commit fc840661206918b5e54322bb557aacb18d9d86eb Author: ModelHub XC Date: Tue Jul 21 18:43:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6f387b4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview-bf16.gguf filter=lfs diff=lfs merge=lfs -text +ibm-granite_granite-4.0-tiny-preview.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d9d20a0 --- /dev/null +++ b/README.md @@ -0,0 +1,173 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: ibm-granite/granite-4.0-tiny-preview +base_model_relation: quantized +license: apache-2.0 +inference: false +tags: +- language +- granite-4.0 +--- + +## Llamacpp imatrix Quantizations of granite-4.0-tiny-preview by ibm-granite + +Using llama.cpp release b5868 for quantization. + +Original model: https://huggingface.co/ibm-granite/granite-4.0-tiny-preview + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|start_of_role|>system<|end_of_role|>{system_prompt}<|end_of_text|> +<|start_of_role|>user<|end_of_role|>{prompt}<|end_of_text|> +<|start_of_role|>assistant<|end_of_role|> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [granite-4.0-tiny-preview-bf16.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-bf16.gguf) | bf16 | 13.35GB | false | Full BF16 weights. | +| [granite-4.0-tiny-preview-Q8_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q8_0.gguf) | Q8_0 | 7.10GB | false | Extremely high quality, generally unneeded but max available quant. | +| [granite-4.0-tiny-preview-Q6_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q6_K_L.gguf) | Q6_K_L | 5.55GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [granite-4.0-tiny-preview-Q6_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q6_K.gguf) | Q6_K | 5.54GB | false | Very high quality, near perfect, *recommended*. | +| [granite-4.0-tiny-preview-Q5_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q5_K_L.gguf) | Q5_K_L | 4.83GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [granite-4.0-tiny-preview-Q5_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q5_K_M.gguf) | Q5_K_M | 4.82GB | false | High quality, *recommended*. | +| [granite-4.0-tiny-preview-Q5_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q5_K_S.gguf) | Q5_K_S | 4.66GB | false | High quality, *recommended*. | +| [granite-4.0-tiny-preview-Q4_1.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q4_1.gguf) | Q4_1 | 4.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [granite-4.0-tiny-preview-Q4_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q4_K_L.gguf) | Q4_K_L | 4.13GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [granite-4.0-tiny-preview-Q4_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q4_K_M.gguf) | Q4_K_M | 4.12GB | false | Good quality, default size for most use cases, *recommended*. | +| [granite-4.0-tiny-preview-Q4_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q4_K_S.gguf) | Q4_K_S | 3.97GB | false | Slightly lower quality with more space savings, *recommended*. | +| [granite-4.0-tiny-preview-Q4_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q4_0.gguf) | Q4_0 | 3.91GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [granite-4.0-tiny-preview-IQ4_NL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-IQ4_NL.gguf) | IQ4_NL | 3.85GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [granite-4.0-tiny-preview-IQ4_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-IQ4_XS.gguf) | IQ4_XS | 3.65GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [granite-4.0-tiny-preview-Q3_K_XL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q3_K_XL.gguf) | Q3_K_XL | 3.27GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [granite-4.0-tiny-preview-Q3_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q3_K_L.gguf) | Q3_K_L | 3.25GB | false | Lower quality but usable, good for low RAM availability. | +| [granite-4.0-tiny-preview-Q3_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q3_K_M.gguf) | Q3_K_M | 3.13GB | false | Low quality. | +| [granite-4.0-tiny-preview-IQ3_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-IQ3_M.gguf) | IQ3_M | 3.13GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [granite-4.0-tiny-preview-Q3_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q3_K_S.gguf) | Q3_K_S | 3.00GB | false | Low quality, not recommended. | +| [granite-4.0-tiny-preview-IQ3_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-IQ3_XS.gguf) | IQ3_XS | 2.87GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [granite-4.0-tiny-preview-IQ3_XXS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-IQ3_XXS.gguf) | IQ3_XXS | 2.74GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [granite-4.0-tiny-preview-Q2_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q2_K_L.gguf) | Q2_K_L | 2.47GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [granite-4.0-tiny-preview-Q2_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-Q2_K.gguf) | Q2_K | 2.45GB | false | Very low quality but surprisingly usable. | +| [granite-4.0-tiny-preview-IQ2_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-tiny-preview-GGUF/blob/main/ibm-granite_granite-4.0-tiny-preview-IQ2_M.gguf) | IQ2_M | 2.18GB | false | Relatively low quality, uses SOTA techniques to be surprisingly 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/ibm-granite_granite-4.0-tiny-preview-GGUF --include "ibm-granite_granite-4.0-tiny-preview-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/ibm-granite_granite-4.0-tiny-preview-GGUF --include "ibm-granite_granite-4.0-tiny-preview-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (ibm-granite_granite-4.0-tiny-preview-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/ggerganov/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/ggerganov/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/ggerganov/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/ggerganov/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/ibm-granite_granite-4.0-tiny-preview-IQ2_M.gguf b/ibm-granite_granite-4.0-tiny-preview-IQ2_M.gguf new file mode 100644 index 0000000..f828ddb --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5f84477614379b0c0c102f531ef45c6533c012647a107dce7fb85e7bfa5989 +size 2176326016 diff --git a/ibm-granite_granite-4.0-tiny-preview-IQ3_M.gguf b/ibm-granite_granite-4.0-tiny-preview-IQ3_M.gguf new file mode 100644 index 0000000..d60c1e8 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcafd81db660a0c20173a2b5ac970c020c982318abee612a9ebe1f0b374ec3bd +size 3132943840 diff --git a/ibm-granite_granite-4.0-tiny-preview-IQ3_XS.gguf b/ibm-granite_granite-4.0-tiny-preview-IQ3_XS.gguf new file mode 100644 index 0000000..e1b04cd --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a978fbfa461423856d04ab70e57b58a8e98500790c4752d5612469d825e747a6 +size 2865434080 diff --git a/ibm-granite_granite-4.0-tiny-preview-IQ3_XXS.gguf b/ibm-granite_granite-4.0-tiny-preview-IQ3_XXS.gguf new file mode 100644 index 0000000..c2d2588 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf168118d5ca9093d9ec716684ee92a59df145d0f7587be8eeaa73e0982d668 +size 2738569600 diff --git a/ibm-granite_granite-4.0-tiny-preview-IQ4_NL.gguf b/ibm-granite_granite-4.0-tiny-preview-IQ4_NL.gguf new file mode 100644 index 0000000..50128ca --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32a7537a6bca16c15df0599f6ed5a80199f053530ad309f38161ee193a93688 +size 3851689696 diff --git a/ibm-granite_granite-4.0-tiny-preview-IQ4_XS.gguf b/ibm-granite_granite-4.0-tiny-preview-IQ4_XS.gguf new file mode 100644 index 0000000..91874fa --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8546b06cfaa4e504d8d168c11eb6d0485f7780af4e8b7d6bebbffa8680eff5ba +size 3652000480 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q2_K.gguf b/ibm-granite_granite-4.0-tiny-preview-Q2_K.gguf new file mode 100644 index 0000000..9f0977b --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e07fb5c5464cae8be4c521e5e3c3b535949c78a049069c9ea0fa9f5c03ccf96 +size 2453381344 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q2_K_L.gguf b/ibm-granite_granite-4.0-tiny-preview-Q2_K_L.gguf new file mode 100644 index 0000000..01c9552 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8dc1342ad8e59a60b85981cc67d869583baae8d97aaedc5babb0b60048577c1 +size 2471668864 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q3_K_L.gguf b/ibm-granite_granite-4.0-tiny-preview-Q3_K_L.gguf new file mode 100644 index 0000000..4983813 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8dbba218d4494c69ad2d3ce406610cf12199aa165aee621be580f24fd476bf +size 3252800992 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q3_K_M.gguf b/ibm-granite_granite-4.0-tiny-preview-Q3_K_M.gguf new file mode 100644 index 0000000..e632e6b --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c095606689d41cc6527a35bba554fc10d130de5110d727aaf7068ffee542a63 +size 3133140448 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q3_K_S.gguf b/ibm-granite_granite-4.0-tiny-preview-Q3_K_S.gguf new file mode 100644 index 0000000..512cb8c --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3714ed0bdbce0c0510d4897527ac3c81168e8e2eb409734b78fe65a1f7b5a486 +size 3003010528 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q3_K_XL.gguf b/ibm-granite_granite-4.0-tiny-preview-Q3_K_XL.gguf new file mode 100644 index 0000000..3e1abc5 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ae305a4a073f2b8facbddf50df6f17f5469c165e46302b269d81b2b290484a +size 3271088512 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q4_0.gguf b/ibm-granite_granite-4.0-tiny-preview-Q4_0.gguf new file mode 100644 index 0000000..e8827de --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365c82160519803b81824eef5babead6032747dbd45d1e114e48ce669bcd2f7c +size 3911458528 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q4_1.gguf b/ibm-granite_granite-4.0-tiny-preview-Q4_1.gguf new file mode 100644 index 0000000..4fb7758 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7463212531607ca43851a5beb7cfd0a15138c761efe46e4a7463bf5d044a8c98 +size 4250478304 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q4_K_L.gguf b/ibm-granite_granite-4.0-tiny-preview-Q4_K_L.gguf new file mode 100644 index 0000000..a40c280 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ec96b841424ee63ca5f3a5ce958761fd803837dc5c0de74c2890b58d976cf7 +size 4134328960 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q4_K_M.gguf b/ibm-granite_granite-4.0-tiny-preview-Q4_K_M.gguf new file mode 100644 index 0000000..93b963c --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b6fc5ad2573a35d317d6a63cb4f3a6195f40d88a27afe8f2b21ef31a028332 +size 4116041440 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q4_K_S.gguf b/ibm-granite_granite-4.0-tiny-preview-Q4_K_S.gguf new file mode 100644 index 0000000..9b91661 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c84389cda63a112484d16cf21fbcdd75630ba5b221e1600c0069d6ea0fd23ad +size 3973979872 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q5_K_L.gguf b/ibm-granite_granite-4.0-tiny-preview-Q5_K_L.gguf new file mode 100644 index 0000000..d63201a --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc8797989fa7560acaf418a024fe6864e61d39a33bf85fd7efce11e2d88624a +size 4833847936 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q5_K_M.gguf b/ibm-granite_granite-4.0-tiny-preview-Q5_K_M.gguf new file mode 100644 index 0000000..ea6ba20 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de211ad86394b7264bb78a622f6422d8446ad36e8ba0ad5813b2329372272e7 +size 4815560416 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q5_K_S.gguf b/ibm-granite_granite-4.0-tiny-preview-Q5_K_S.gguf new file mode 100644 index 0000000..369df4a --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be42eeeec5f620bf0179552f0ab501f68694ef176e66cef8260ea6df59a94aed +size 4662980320 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q6_K.gguf b/ibm-granite_granite-4.0-tiny-preview-Q6_K.gguf new file mode 100644 index 0000000..d69cd4a --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d7ab328ba18c54ff3243f7e8d1c0d44487188aa42d6476a97057812f9a0f61 +size 5535768544 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q6_K_L.gguf b/ibm-granite_granite-4.0-tiny-preview-Q6_K_L.gguf new file mode 100644 index 0000000..b1a88d0 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af252b0230e94bba226caf4391a7af9e133ba0f13d7af48b66cecf1b245eded +size 5554056064 diff --git a/ibm-granite_granite-4.0-tiny-preview-Q8_0.gguf b/ibm-granite_granite-4.0-tiny-preview-Q8_0.gguf new file mode 100644 index 0000000..76bf5d8 --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7f4dfcf49bdf981cfc99c0d361650a788597d7af59eec8f6a619f0e8a5d116 +size 7103933056 diff --git a/ibm-granite_granite-4.0-tiny-preview-bf16.gguf b/ibm-granite_granite-4.0-tiny-preview-bf16.gguf new file mode 100644 index 0000000..a95739e --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8adb5bd7a28aafd804c17aac8ef243803bb46fc26045b1f4eff16e83c503f308 +size 13354143616 diff --git a/ibm-granite_granite-4.0-tiny-preview.imatrix b/ibm-granite_granite-4.0-tiny-preview.imatrix new file mode 100644 index 0000000..daabe2b --- /dev/null +++ b/ibm-granite_granite-4.0-tiny-preview.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1832f25b5ae583fd411946fdc093fb693f6072d91122f7193d5f98a02dbd01b +size 35452036