commit a800e83b50ddd068538a827ca1d9a2b76a34c5cc Author: ModelHub XC Date: Mon Jul 27 08:18:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3c16867 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,75 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +utter-project_EuroLLM-22B-Instruct-2512-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-bf16.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +utter-project_EuroLLM-22B-Instruct-2512-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..ef82a98 --- /dev/null +++ b/README.md @@ -0,0 +1,209 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: utter-project/EuroLLM-22B-Instruct-2512 +license: apache-2.0 +language: +- en +- de +- es +- fr +- it +- pt +- pl +- nl +- tr +- sv +- cs +- el +- hu +- ro +- fi +- uk +- sl +- sk +- da +- lt +- lv +- et +- bg +- 'no' +- ca +- hr +- ga +- mt +- gl +- zh +- ru +- ko +- ja +- ar +- hi +--- + +## Llamacpp imatrix Quantizations of EuroLLM-22B-Instruct-2512 by utter-project + +Using llama.cpp release b7406 for quantization. + +Original model: https://huggingface.co/utter-project/EuroLLM-22B-Instruct-2512 + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [EuroLLM-22B-Instruct-2512-bf16.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-bf16.gguf) | bf16 | 45.28GB | false | Full BF16 weights. | +| [EuroLLM-22B-Instruct-2512-Q8_0.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q8_0.gguf) | Q8_0 | 24.06GB | false | Extremely high quality, generally unneeded but max available quant. | +| [EuroLLM-22B-Instruct-2512-Q6_K_L.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q6_K_L.gguf) | Q6_K_L | 18.96GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q6_K.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q6_K.gguf) | Q6_K | 18.57GB | false | Very high quality, near perfect, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q5_K_L.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_L.gguf) | Q5_K_L | 16.53GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q5_K_M.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_M.gguf) | Q5_K_M | 16.04GB | false | High quality, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q5_K_S.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_S.gguf) | Q5_K_S | 15.67GB | false | High quality, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q4_1.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q4_1.gguf) | Q4_1 | 14.31GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [EuroLLM-22B-Instruct-2512-Q4_K_L.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_L.gguf) | Q4_K_L | 14.24GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q4_K_M.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_M.gguf) | Q4_K_M | 13.66GB | false | Good quality, default size for most use cases, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q4_K_S.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_S.gguf) | Q4_K_S | 13.02GB | false | Slightly lower quality with more space savings, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q4_0.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q4_0.gguf) | Q4_0 | 12.98GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [EuroLLM-22B-Instruct-2512-IQ4_NL.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-IQ4_NL.gguf) | IQ4_NL | 12.98GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [EuroLLM-22B-Instruct-2512-Q3_K_XL.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_XL.gguf) | Q3_K_XL | 12.74GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [EuroLLM-22B-Instruct-2512-IQ4_XS.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-IQ4_XS.gguf) | IQ4_XS | 12.31GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [EuroLLM-22B-Instruct-2512-Q3_K_L.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_L.gguf) | Q3_K_L | 12.05GB | false | Lower quality but usable, good for low RAM availability. | +| [EuroLLM-22B-Instruct-2512-Q3_K_M.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_M.gguf) | Q3_K_M | 11.12GB | false | Low quality. | +| [EuroLLM-22B-Instruct-2512-IQ3_M.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-IQ3_M.gguf) | IQ3_M | 10.44GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [EuroLLM-22B-Instruct-2512-Q3_K_S.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_S.gguf) | Q3_K_S | 10.04GB | false | Low quality, not recommended. | +| [EuroLLM-22B-Instruct-2512-IQ3_XS.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-IQ3_XS.gguf) | IQ3_XS | 9.59GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [EuroLLM-22B-Instruct-2512-Q2_K_L.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q2_K_L.gguf) | Q2_K_L | 9.43GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [EuroLLM-22B-Instruct-2512-IQ3_XXS.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-IQ3_XXS.gguf) | IQ3_XXS | 8.96GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [EuroLLM-22B-Instruct-2512-Q2_K.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-Q2_K.gguf) | Q2_K | 8.66GB | false | Very low quality but surprisingly usable. | +| [EuroLLM-22B-Instruct-2512-IQ2_M.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-IQ2_M.gguf) | IQ2_M | 8.00GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [EuroLLM-22B-Instruct-2512-IQ2_S.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-IQ2_S.gguf) | IQ2_S | 7.44GB | false | Low quality, uses SOTA techniques to be usable. | +| [EuroLLM-22B-Instruct-2512-IQ2_XS.gguf](https://huggingface.co/bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF/blob/main/utter-project_EuroLLM-22B-Instruct-2512-IQ2_XS.gguf) | IQ2_XS | 7.01GB | false | Low quality, uses SOTA techniques to be usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF --include "utter-project_EuroLLM-22B-Instruct-2512-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF --include "utter-project_EuroLLM-22B-Instruct-2512-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (utter-project_EuroLLM-22B-Instruct-2512-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/utter-project_EuroLLM-22B-Instruct-2512-IQ2_M.gguf b/utter-project_EuroLLM-22B-Instruct-2512-IQ2_M.gguf new file mode 100644 index 0000000..a5fc0a4 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1596084cb005bfe876e672c0ff757a9aafe1af5b9f509bcb6272a54f72c0370 +size 8002655520 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-IQ2_S.gguf b/utter-project_EuroLLM-22B-Instruct-2512-IQ2_S.gguf new file mode 100644 index 0000000..680c1b6 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d9809849a3873aa0112a92a54990b1e5df9402fce9f44ae53ff304b999db5a +size 7437604128 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-IQ2_XS.gguf b/utter-project_EuroLLM-22B-Instruct-2512-IQ2_XS.gguf new file mode 100644 index 0000000..9b5777e --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eabc0398ba9db948077fc7217e753d02298c625f958c79c2055c1c36dc914b9 +size 7009735968 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-IQ3_M.gguf b/utter-project_EuroLLM-22B-Instruct-2512-IQ3_M.gguf new file mode 100644 index 0000000..af68220 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3e330a3ef8d0fb0cfeb074c468710daeb9a75bc75510a56b8bc4e84a10e2d7 +size 10435728672 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-IQ3_XS.gguf b/utter-project_EuroLLM-22B-Instruct-2512-IQ3_XS.gguf new file mode 100644 index 0000000..c6dfc05 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f81474158dc432265d60b77d0ef78388000b26563f989ebfb2c84647fb08c4 +size 9586382112 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-IQ3_XXS.gguf b/utter-project_EuroLLM-22B-Instruct-2512-IQ3_XXS.gguf new file mode 100644 index 0000000..2db90c0 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11bde6a20ef0043e66bca9ee6ad4c6d85f69aa7f31bee73bd5f806445a17ee44 +size 8955811104 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-IQ4_NL.gguf b/utter-project_EuroLLM-22B-Instruct-2512-IQ4_NL.gguf new file mode 100644 index 0000000..aa454d8 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356f609ff9b8afa81a8d300c0d41242e5fe63e1ab0134268556ec7d7ac5d7374 +size 12984112416 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-IQ4_XS.gguf b/utter-project_EuroLLM-22B-Instruct-2512-IQ4_XS.gguf new file mode 100644 index 0000000..6f0ad7d --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f97376bd177f9f5a687c7ed106cbd2f4f896603f156e097a70db03f0ba7da2a +size 12311909664 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q2_K.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q2_K.gguf new file mode 100644 index 0000000..c849108 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ceb9bd4f0c0f762f01ece23d6a5b1a35d706671364978746d281f717c08e7d6 +size 8659227936 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q2_K_L.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q2_K_L.gguf new file mode 100644 index 0000000..5d8ce2d --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1334695044dae0835c2ed250634fc3f6ff198e4fe59504487d6970081bf1e34 +size 9427227936 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_L.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_L.gguf new file mode 100644 index 0000000..22d3349 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2e433890beb21fd7beb3a2747016053dcd57462b8925cf27db9ac5aea73207c +size 12054205728 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_M.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_M.gguf new file mode 100644 index 0000000..ecf6960 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77e974487a848e0a1286dc64f93364266d0fc12b957755b9f5f602a2401a330 +size 11116778784 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_S.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_S.gguf new file mode 100644 index 0000000..37829d7 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ced50d89e34934964f2482f024a65e7e9658c6ed0cca94296b0b63e36cf5b8 +size 10039661856 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_XL.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_XL.gguf new file mode 100644 index 0000000..ea51884 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92212bdd9d77ac1c9ebc730c749f03e777887d63371cca10c198aa31ad35b941 +size 12742333728 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q4_0.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q4_0.gguf new file mode 100644 index 0000000..3ce160d --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e0f7085c41ca53d95120cc0abd6d1c24158b50f258b28c49c526b327842fff +size 12979393824 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q4_1.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q4_1.gguf new file mode 100644 index 0000000..18f13ec --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275a07e81bf0999b0fc19e3122a6143e6755278d3ce458808e3c83a49e22e41f +size 14307284256 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_L.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_L.gguf new file mode 100644 index 0000000..71f48cc --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:057c986ed297584b4420147d4e47ef366cbed99217b3433cfed1a141226d4ee6 +size 14242256160 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_M.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_M.gguf new file mode 100644 index 0000000..ce2e62e --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a222374c4adacd55b55795e2f9dca42a2f100d5a2d5858442f928c4c8bdf5e7 +size 13658576160 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_S.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_S.gguf new file mode 100644 index 0000000..13686f3 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42270babbd9a0fd9b601bb9583b076710fb6ee4e8bd48ce377f7d73fd3fd5194 +size 13020288288 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_L.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_L.gguf new file mode 100644 index 0000000..7f509fc --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21445c02e0987c80c64f3d2d551147d61bae7faee65801f017f169a9b4934d5 +size 16527627552 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_M.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_M.gguf new file mode 100644 index 0000000..f0bdd1b --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f99634b10acfa8c4c5356e88b06b9c559bb32d41409be9d99d39e169b01bb1 +size 16042251552 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_S.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_S.gguf new file mode 100644 index 0000000..c8f7880 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eded21b1e4d59e9ca04badb02b6a2a1ff34ab8b53adde5a103d3029c75d1cb3 +size 15672923424 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q6_K.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q6_K.gguf new file mode 100644 index 0000000..7d8b690 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11015044dc0d531b7f75a8f0714e377e4bfd7f86ef6ed3b5a1b10a47ab0080d5 +size 18574906656 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q6_K_L.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q6_K_L.gguf new file mode 100644 index 0000000..c7e47ca --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9aa37842fa18f319930332c869044f4f39be69f316e7639f95686abed28cfd +size 18955834656 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-Q8_0.gguf b/utter-project_EuroLLM-22B-Instruct-2512-Q8_0.gguf new file mode 100644 index 0000000..2fe3078 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d67bdc6d98fa7c7cf2ee0be094f5b57cfa227d28b31bfa7ffbf88c69beb90d +size 24057222432 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-bf16.gguf b/utter-project_EuroLLM-22B-Instruct-2512-bf16.gguf new file mode 100644 index 0000000..6063e0c --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6b916d4f9042d18a2a1e618b0a0ee4ea40945c16ac01319ce0e6284f3a8b38 +size 45279089632 diff --git a/utter-project_EuroLLM-22B-Instruct-2512-imatrix.gguf b/utter-project_EuroLLM-22B-Instruct-2512-imatrix.gguf new file mode 100644 index 0000000..720eb69 --- /dev/null +++ b/utter-project_EuroLLM-22B-Instruct-2512-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d05131284b4d8fea8d6885f41cd987e96dbdd47a9f5a0f2fe17a8c47b83612 +size 11559712