commit d4056350b98ee265264aa958e21f73c3627c146c Author: ModelHub XC Date: Wed Jul 29 17:45:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/mistralai_Magistral-Small-2509-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..033c896 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,76 @@ +*.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 + +mistralai_Magistral-Small-2509-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-bf16.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Magistral-Small-2509-Q6_K_L.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..78e6365 --- /dev/null +++ b/README.md @@ -0,0 +1,167 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: mistralai/Magistral-Small-2509 +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Magistral-Small-2509 by mistralai + +Using llama.cpp release b6490 for quantization. + +Original model: https://huggingface.co/mistralai/Magistral-Small-2509 + +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 + +No prompt format found, check original model page + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Magistral-Small-2509-bf16.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-bf16.gguf) | bf16 | 47.15GB | false | Full BF16 weights. | +| [Magistral-Small-2509-Q8_0.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q8_0.gguf) | Q8_0 | 25.05GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Magistral-Small-2509-Q6_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q6_K_L.gguf) | Q6_K_L | 19.67GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Magistral-Small-2509-Q6_K.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q6_K.gguf) | Q6_K | 19.35GB | false | Very high quality, near perfect, *recommended*. | +| [Magistral-Small-2509-Q5_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q5_K_L.gguf) | Q5_K_L | 17.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Magistral-Small-2509-Q5_K_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q5_K_M.gguf) | Q5_K_M | 16.76GB | false | High quality, *recommended*. | +| [Magistral-Small-2509-Q5_K_S.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q5_K_S.gguf) | Q5_K_S | 16.30GB | false | High quality, *recommended*. | +| [Magistral-Small-2509-Q4_1.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q4_1.gguf) | Q4_1 | 14.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Magistral-Small-2509-Q4_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q4_K_L.gguf) | Q4_K_L | 14.83GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Magistral-Small-2509-Q4_K_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q4_K_M.gguf) | Q4_K_M | 14.33GB | false | Good quality, default size for most use cases, *recommended*. | +| [Magistral-Small-2509-Q4_K_S.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q4_K_S.gguf) | Q4_K_S | 13.55GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Magistral-Small-2509-Q4_0.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q4_0.gguf) | Q4_0 | 13.49GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Magistral-Small-2509-IQ4_NL.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ4_NL.gguf) | IQ4_NL | 13.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Magistral-Small-2509-Q3_K_XL.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q3_K_XL.gguf) | Q3_K_XL | 12.99GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Magistral-Small-2509-IQ4_XS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ4_XS.gguf) | IQ4_XS | 12.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Magistral-Small-2509-Q3_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q3_K_L.gguf) | Q3_K_L | 12.40GB | false | Lower quality but usable, good for low RAM availability. | +| [Magistral-Small-2509-Q3_K_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q3_K_M.gguf) | Q3_K_M | 11.47GB | false | Low quality. | +| [Magistral-Small-2509-IQ3_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ3_M.gguf) | IQ3_M | 10.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Magistral-Small-2509-Q3_K_S.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q3_K_S.gguf) | Q3_K_S | 10.40GB | false | Low quality, not recommended. | +| [Magistral-Small-2509-IQ3_XS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ3_XS.gguf) | IQ3_XS | 9.91GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Magistral-Small-2509-Q2_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q2_K_L.gguf) | Q2_K_L | 9.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Magistral-Small-2509-IQ3_XXS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ3_XXS.gguf) | IQ3_XXS | 9.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Magistral-Small-2509-Q2_K.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-Q2_K.gguf) | Q2_K | 8.89GB | false | Very low quality but surprisingly usable. | +| [Magistral-Small-2509-IQ2_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ2_M.gguf) | IQ2_M | 8.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Magistral-Small-2509-IQ2_S.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ2_S.gguf) | IQ2_S | 7.48GB | false | Low quality, uses SOTA techniques to be usable. | +| [Magistral-Small-2509-IQ2_XS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ2_XS.gguf) | IQ2_XS | 7.21GB | false | Low quality, uses SOTA techniques to be usable. | +| [Magistral-Small-2509-IQ2_XXS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2509-GGUF/blob/main/mistralai_Magistral-Small-2509-IQ2_XXS.gguf) | IQ2_XXS | 6.55GB | false | Very 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/mistralai_Magistral-Small-2509-GGUF --include "mistralai_Magistral-Small-2509-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/mistralai_Magistral-Small-2509-GGUF --include "mistralai_Magistral-Small-2509-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (mistralai_Magistral-Small-2509-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/mistralai_Magistral-Small-2509-IQ2_M.gguf b/mistralai_Magistral-Small-2509-IQ2_M.gguf new file mode 100644 index 0000000..79d7f1a --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6ffe5babd5cbc246597f7882b1e9376c6f0eab4c9e45ffb84c4135f110f5ec +size 8114054112 diff --git a/mistralai_Magistral-Small-2509-IQ2_S.gguf b/mistralai_Magistral-Small-2509-IQ2_S.gguf new file mode 100644 index 0000000..ae12461 --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c773bb71d4d28d0d1eb75087c03dec27dd6d593e4a486a6dd1cd68bd7dced1 +size 7478354912 diff --git a/mistralai_Magistral-Small-2509-IQ2_XS.gguf b/mistralai_Magistral-Small-2509-IQ2_XS.gguf new file mode 100644 index 0000000..2125750 --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b922cac917abbb373d2b214d1e3bb9354fea46c49f0f62452751b9f8d96e263b +size 7207035872 diff --git a/mistralai_Magistral-Small-2509-IQ2_XXS.gguf b/mistralai_Magistral-Small-2509-IQ2_XXS.gguf new file mode 100644 index 0000000..3a20574 --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9884b0c753c41decfa7ec618c76710b7d8d7303b4721093912341459ebd4fd10 +size 6545122272 diff --git a/mistralai_Magistral-Small-2509-IQ3_M.gguf b/mistralai_Magistral-Small-2509-IQ3_M.gguf new file mode 100644 index 0000000..d6cc0d1 --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f920b3eefcaf714db8a735cfe2c7993ca0c555a262335f5a4e8b14ac6fc77bf6 +size 10650952672 diff --git a/mistralai_Magistral-Small-2509-IQ3_XS.gguf b/mistralai_Magistral-Small-2509-IQ3_XS.gguf new file mode 100644 index 0000000..b6827c0 --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb63f0231597c176f4115945c326143aebf683133f2c248b8b4543d50c78d0e +size 9907119072 diff --git a/mistralai_Magistral-Small-2509-IQ3_XXS.gguf b/mistralai_Magistral-Small-2509-IQ3_XXS.gguf new file mode 100644 index 0000000..58a42d9 --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c03de8c57d07f977b1b5c837de67d78abaf79d75dd1156e7cd9e134a198094e0 +size 9280594912 diff --git a/mistralai_Magistral-Small-2509-IQ4_NL.gguf b/mistralai_Magistral-Small-2509-IQ4_NL.gguf new file mode 100644 index 0000000..ded24fb --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddcd6be84838f89328a29933810e4ff52649d135afc585772aab6ee72aa1afd +size 13468017632 diff --git a/mistralai_Magistral-Small-2509-IQ4_XS.gguf b/mistralai_Magistral-Small-2509-IQ4_XS.gguf new file mode 100644 index 0000000..3f45dfe --- /dev/null +++ b/mistralai_Magistral-Small-2509-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f1665923e9045f8ff3b5617b0450c7031207030f052f64a45669e7da6f4e7f +size 12758918112 diff --git a/mistralai_Magistral-Small-2509-Q2_K.gguf b/mistralai_Magistral-Small-2509-Q2_K.gguf new file mode 100644 index 0000000..4c1a594 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5ad91c21aca44e81338377647284842aed1f37e1f00dbafb770dbb4bba8790 +size 8890328032 diff --git a/mistralai_Magistral-Small-2509-Q2_K_L.gguf b/mistralai_Magistral-Small-2509-Q2_K_L.gguf new file mode 100644 index 0000000..affbaa8 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558b3dc07b399483b17bfc2fededba900748c4f96cde975417978f8ae955605e +size 9545688032 diff --git a/mistralai_Magistral-Small-2509-Q3_K_L.gguf b/mistralai_Magistral-Small-2509-Q3_K_L.gguf new file mode 100644 index 0000000..3efa37a --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599792a7651d970c4f511697e33dea3a1d9dcbea17d7b8de5a0c84b0c28d97c8 +size 12400763872 diff --git a/mistralai_Magistral-Small-2509-Q3_K_M.gguf b/mistralai_Magistral-Small-2509-Q3_K_M.gguf new file mode 100644 index 0000000..8064b97 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9937a2ee0275035e1cc918d6dc961649d09a812d3b6216165bf902ae2fa06a4 +size 11474084832 diff --git a/mistralai_Magistral-Small-2509-Q3_K_S.gguf b/mistralai_Magistral-Small-2509-Q3_K_S.gguf new file mode 100644 index 0000000..eb67437 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41cdae33f5e8a42e32b61cc7f61f4c8b3136466a7a75513c85f3bf3eafbc2b2 +size 10400277472 diff --git a/mistralai_Magistral-Small-2509-Q3_K_XL.gguf b/mistralai_Magistral-Small-2509-Q3_K_XL.gguf new file mode 100644 index 0000000..092d13a --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8fc49b03739c0454af657c53d8fa2a01826ea5573d7d2cfa94055febdebcd4 +size 12987966432 diff --git a/mistralai_Magistral-Small-2509-Q4_0.gguf b/mistralai_Magistral-Small-2509-Q4_0.gguf new file mode 100644 index 0000000..211e61d --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b299c75a71044eb771d189617e59228432dcd1c2b6858f71727e2fc560fae814 +size 13494232032 diff --git a/mistralai_Magistral-Small-2509-Q4_1.gguf b/mistralai_Magistral-Small-2509-Q4_1.gguf new file mode 100644 index 0000000..624c290 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8ba1bf044cdaaee9b9013a9ea00cea279cc63c9aeccbe1a11751aa675c17f5 +size 14873109472 diff --git a/mistralai_Magistral-Small-2509-Q4_K_L.gguf b/mistralai_Magistral-Small-2509-Q4_K_L.gguf new file mode 100644 index 0000000..4044173 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3227a9b00357f4e337a0f01727c5ebb6b0b1cfdbe36bcb04ecfe1a148bd44424 +size 14831985632 diff --git a/mistralai_Magistral-Small-2509-Q4_K_M.gguf b/mistralai_Magistral-Small-2509-Q4_K_M.gguf new file mode 100644 index 0000000..211e598 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d638bc931de30d29fc73ad439206ff185f76666a096e7ad723866a20f78728d +size 14333912032 diff --git a/mistralai_Magistral-Small-2509-Q4_K_S.gguf b/mistralai_Magistral-Small-2509-Q4_K_S.gguf new file mode 100644 index 0000000..b25411c --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b311cb7c6652eca5ac99f083a76dbfded4073067c2600a32b36e0b0033b45f +size 13549282272 diff --git a/mistralai_Magistral-Small-2509-Q5_K_L.gguf b/mistralai_Magistral-Small-2509-Q5_K_L.gguf new file mode 100644 index 0000000..3780b43 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa95ce60f6114226e8194ce3e03b92047728b3f9971e88ef92a3b1bc7c0c4701 +size 17178174432 diff --git a/mistralai_Magistral-Small-2509-Q5_K_M.gguf b/mistralai_Magistral-Small-2509-Q5_K_M.gguf new file mode 100644 index 0000000..931b275 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b9cfee8fb41bd363aa5feda66f3d66abb003801b000a75afb9f0cb833ea18c8 +size 16763986912 diff --git a/mistralai_Magistral-Small-2509-Q5_K_S.gguf b/mistralai_Magistral-Small-2509-Q5_K_S.gguf new file mode 100644 index 0000000..4c30a3e --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad91cd0297a0747257adc9d3486074d59e1383eaf4a7738bf8ebd35fd62e46c0 +size 16304415712 diff --git a/mistralai_Magistral-Small-2509-Q6_K.gguf b/mistralai_Magistral-Small-2509-Q6_K.gguf new file mode 100644 index 0000000..e8a6240 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d28f624b8d526df0bbaaaaf68ede7349eb8a599d458ec7d50bc159339d053f7 +size 19345941472 diff --git a/mistralai_Magistral-Small-2509-Q6_K_L.gguf b/mistralai_Magistral-Small-2509-Q6_K_L.gguf new file mode 100644 index 0000000..1ef145d --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de12e1ab2027da9155b148114ccf6a30bff606a4597d05b4c7a114b0b370289b +size 19671000032 diff --git a/mistralai_Magistral-Small-2509-Q8_0.gguf b/mistralai_Magistral-Small-2509-Q8_0.gguf new file mode 100644 index 0000000..4b96cc2 --- /dev/null +++ b/mistralai_Magistral-Small-2509-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a067b77005461b127a1c7455709c588668d53814cdf801c7091145207774841 +size 25054782432 diff --git a/mistralai_Magistral-Small-2509-bf16.gguf b/mistralai_Magistral-Small-2509-bf16.gguf new file mode 100644 index 0000000..c256147 --- /dev/null +++ b/mistralai_Magistral-Small-2509-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e6727234a1b138bdf6ffd508b137166a51a44cd7d1e0413c45d91a80d2b994 +size 47153521344 diff --git a/mistralai_Magistral-Small-2509-imatrix.gguf b/mistralai_Magistral-Small-2509-imatrix.gguf new file mode 100644 index 0000000..9936b15 --- /dev/null +++ b/mistralai_Magistral-Small-2509-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3825d793387a5961f5ed99b6047ca880ca4ad60224ca40c47ed155159d6f774f +size 10037344