commit 83570452d7f64f006096fef1b91af138a65d3edf Author: ModelHub XC Date: Thu Jun 4 00:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/mistralai_Voxtral-Small-24B-2507-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9df847c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,64 @@ +*.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 +mistralai_Voxtral-Small-24B-2507-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-bf16.gguf filter=lfs diff=lfs merge=lfs -text +mistralai_Voxtral-Small-24B-2507-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-mistralai_Voxtral-Small-24B-2507-f16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-mistralai_Voxtral-Small-24B-2507-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a9890bf --- /dev/null +++ b/README.md @@ -0,0 +1,166 @@ +--- +quantized_by: bartowski +pipeline_tag: audio-text-to-text +base_model_relation: quantized +base_model: mistralai/Voxtral-Small-24B-2507 +--- + +## Llamacpp imatrix Quantizations of Voxtral-Small-24B-2507 by mistralai + +Using llama.cpp release b6014 for quantization. + +Original model: https://huggingface.co/mistralai/Voxtral-Small-24B-2507 + +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 + +No prompt format found, check original model page + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Voxtral-Small-24B-2507-bf16.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-bf16.gguf) | bf16 | 47.15GB | false | Full BF16 weights. | +| [Voxtral-Small-24B-2507-Q8_0.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q8_0.gguf) | Q8_0 | 25.06GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Voxtral-Small-24B-2507-Q6_K_L.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q6_K_L.gguf) | Q6_K_L | 19.67GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Voxtral-Small-24B-2507-Q6_K.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q6_K.gguf) | Q6_K | 19.35GB | false | Very high quality, near perfect, *recommended*. | +| [Voxtral-Small-24B-2507-Q5_K_L.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q5_K_L.gguf) | Q5_K_L | 17.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Voxtral-Small-24B-2507-Q5_K_M.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q5_K_M.gguf) | Q5_K_M | 16.76GB | false | High quality, *recommended*. | +| [Voxtral-Small-24B-2507-Q5_K_S.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q5_K_S.gguf) | Q5_K_S | 16.30GB | false | High quality, *recommended*. | +| [Voxtral-Small-24B-2507-Q4_1.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q4_1.gguf) | Q4_1 | 14.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Voxtral-Small-24B-2507-Q4_K_L.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q4_K_L.gguf) | Q4_K_L | 14.83GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Voxtral-Small-24B-2507-Q4_K_M.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q4_K_M.gguf) | Q4_K_M | 14.33GB | false | Good quality, default size for most use cases, *recommended*. | +| [Voxtral-Small-24B-2507-Q4_K_S.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q4_K_S.gguf) | Q4_K_S | 13.55GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Voxtral-Small-24B-2507-Q4_0.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q4_0.gguf) | Q4_0 | 13.49GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Voxtral-Small-24B-2507-IQ4_NL.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-IQ4_NL.gguf) | IQ4_NL | 13.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Voxtral-Small-24B-2507-Q3_K_XL.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-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. | +| [Voxtral-Small-24B-2507-IQ4_XS.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-IQ4_XS.gguf) | IQ4_XS | 12.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Voxtral-Small-24B-2507-Q3_K_L.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q3_K_L.gguf) | Q3_K_L | 12.40GB | false | Lower quality but usable, good for low RAM availability. | +| [Voxtral-Small-24B-2507-Q3_K_M.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q3_K_M.gguf) | Q3_K_M | 11.47GB | false | Low quality. | +| [Voxtral-Small-24B-2507-IQ3_M.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-IQ3_M.gguf) | IQ3_M | 10.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Voxtral-Small-24B-2507-Q3_K_S.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q3_K_S.gguf) | Q3_K_S | 10.40GB | false | Low quality, not recommended. | +| [Voxtral-Small-24B-2507-IQ3_XS.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-IQ3_XS.gguf) | IQ3_XS | 9.91GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Voxtral-Small-24B-2507-Q2_K_L.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q2_K_L.gguf) | Q2_K_L | 9.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Voxtral-Small-24B-2507-IQ3_XXS.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-IQ3_XXS.gguf) | IQ3_XXS | 9.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Voxtral-Small-24B-2507-Q2_K.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-Q2_K.gguf) | Q2_K | 8.89GB | false | Very low quality but surprisingly usable. | +| [Voxtral-Small-24B-2507-IQ2_M.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-IQ2_M.gguf) | IQ2_M | 8.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Voxtral-Small-24B-2507-IQ2_S.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-IQ2_S.gguf) | IQ2_S | 7.48GB | false | Low quality, uses SOTA techniques to be usable. | +| [Voxtral-Small-24B-2507-IQ2_XS.gguf](https://huggingface.co/bartowski/mistralai_Voxtral-Small-24B-2507-GGUF/blob/main/mistralai_Voxtral-Small-24B-2507-IQ2_XS.gguf) | IQ2_XS | 7.21GB | 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/mistralai_Voxtral-Small-24B-2507-GGUF --include "mistralai_Voxtral-Small-24B-2507-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_Voxtral-Small-24B-2507-GGUF --include "mistralai_Voxtral-Small-24B-2507-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (mistralai_Voxtral-Small-24B-2507-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 \ No newline at end of file diff --git a/mistralai_Voxtral-Small-24B-2507-IQ2_M.gguf b/mistralai_Voxtral-Small-24B-2507-IQ2_M.gguf new file mode 100644 index 0000000..9d39fee --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c008d3cf023222a720f5892d41ec9ac1e7a87c5096fe91fab44b1dfc4dce91ea +size 8114584512 diff --git a/mistralai_Voxtral-Small-24B-2507-IQ2_S.gguf b/mistralai_Voxtral-Small-24B-2507-IQ2_S.gguf new file mode 100644 index 0000000..f84e8e2 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebcca6f8d0f83ab8f2372e2c9643053d9c996646ff972ad73782f116c86274c1 +size 7478885312 diff --git a/mistralai_Voxtral-Small-24B-2507-IQ2_XS.gguf b/mistralai_Voxtral-Small-24B-2507-IQ2_XS.gguf new file mode 100644 index 0000000..c626e4c --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b5ae0aba66bf75c91f2dc71871be24a6b466042a30f55c571a5dada15f6d857 +size 7207566272 diff --git a/mistralai_Voxtral-Small-24B-2507-IQ3_M.gguf b/mistralai_Voxtral-Small-24B-2507-IQ3_M.gguf new file mode 100644 index 0000000..20954f4 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640bb79a5a37e342e8d58b1498985ac807511ce6fc914cbf037ffc4db782db2a +size 10651483072 diff --git a/mistralai_Voxtral-Small-24B-2507-IQ3_XS.gguf b/mistralai_Voxtral-Small-24B-2507-IQ3_XS.gguf new file mode 100644 index 0000000..b599858 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e47329fb73a5e7d12fd1e070076b4d0496c19b5f61fa9fa97156537cfb4001 +size 9907649472 diff --git a/mistralai_Voxtral-Small-24B-2507-IQ3_XXS.gguf b/mistralai_Voxtral-Small-24B-2507-IQ3_XXS.gguf new file mode 100644 index 0000000..2bb6a53 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efffd4b6b893c1b63b2fe121bfedbe23503552b40902a2e6bb0c484419e4c7c7 +size 9281125312 diff --git a/mistralai_Voxtral-Small-24B-2507-IQ4_NL.gguf b/mistralai_Voxtral-Small-24B-2507-IQ4_NL.gguf new file mode 100644 index 0000000..8bf216a --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63aa8c097132c2f96de7af0427891963b565eff2cf27e56de3d9830a8dd7d3de +size 13468548032 diff --git a/mistralai_Voxtral-Small-24B-2507-IQ4_XS.gguf b/mistralai_Voxtral-Small-24B-2507-IQ4_XS.gguf new file mode 100644 index 0000000..e8e8337 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1654a4fcfe788ea6e1c60db4526569ce42b7eb7369143cae72b153be0955a76a +size 12759448512 diff --git a/mistralai_Voxtral-Small-24B-2507-Q2_K.gguf b/mistralai_Voxtral-Small-24B-2507-Q2_K.gguf new file mode 100644 index 0000000..0209fd4 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6b29eb5cc282585c4c94b7a791c94b02d2ce0446afe2339da7bfe8434ea88a +size 8890858432 diff --git a/mistralai_Voxtral-Small-24B-2507-Q2_K_L.gguf b/mistralai_Voxtral-Small-24B-2507-Q2_K_L.gguf new file mode 100644 index 0000000..ea7f531 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b11b2d39e5e123743b5dd772f23226dc637f4129cd23a2efd5cedfce2daee5e2 +size 9546218432 diff --git a/mistralai_Voxtral-Small-24B-2507-Q3_K_L.gguf b/mistralai_Voxtral-Small-24B-2507-Q3_K_L.gguf new file mode 100644 index 0000000..c390a14 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a698a078567b9fdcc7e3f65d055ad041edfa9dda4eeec38150abb1413cb7eb +size 12401294272 diff --git a/mistralai_Voxtral-Small-24B-2507-Q3_K_M.gguf b/mistralai_Voxtral-Small-24B-2507-Q3_K_M.gguf new file mode 100644 index 0000000..c4ad50a --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2fc4f1f284c4033e167d2ae7cad078b1fa6b58072ea5a1aea0e3a981311e0ef +size 11474615232 diff --git a/mistralai_Voxtral-Small-24B-2507-Q3_K_S.gguf b/mistralai_Voxtral-Small-24B-2507-Q3_K_S.gguf new file mode 100644 index 0000000..6283745 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e54310acd5c6f1f061051c1008d458abbdc187f55fc691d12fcc6ffaccf62bd +size 10400807872 diff --git a/mistralai_Voxtral-Small-24B-2507-Q3_K_XL.gguf b/mistralai_Voxtral-Small-24B-2507-Q3_K_XL.gguf new file mode 100644 index 0000000..4cbe7e8 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a728fb1e84843cc24ad2c3124eed6bd7a5d466178e3f1b4bff6166328e82f8 +size 12988496832 diff --git a/mistralai_Voxtral-Small-24B-2507-Q4_0.gguf b/mistralai_Voxtral-Small-24B-2507-Q4_0.gguf new file mode 100644 index 0000000..a9667ac --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd9091e1229da4c04c01dad1a865dfc000699e37b07bbc53948e4593816fe04c +size 13494762432 diff --git a/mistralai_Voxtral-Small-24B-2507-Q4_1.gguf b/mistralai_Voxtral-Small-24B-2507-Q4_1.gguf new file mode 100644 index 0000000..ab57303 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d054a55ae7a1be4b0b390710f6880c0bb8c7ab641bcd99919d1f9971f173a1c3 +size 14873639872 diff --git a/mistralai_Voxtral-Small-24B-2507-Q4_K_L.gguf b/mistralai_Voxtral-Small-24B-2507-Q4_K_L.gguf new file mode 100644 index 0000000..6d4ddeb --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599d0235a51bad741e49729271cd5584d972ea9a72f542b16406c8e5ebcc80ad +size 14832516032 diff --git a/mistralai_Voxtral-Small-24B-2507-Q4_K_M.gguf b/mistralai_Voxtral-Small-24B-2507-Q4_K_M.gguf new file mode 100644 index 0000000..cb5293d --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f8b22205223a1078f6e6fce344185e966916efbcb0bed54429a549d82a72f3 +size 14334442432 diff --git a/mistralai_Voxtral-Small-24B-2507-Q4_K_S.gguf b/mistralai_Voxtral-Small-24B-2507-Q4_K_S.gguf new file mode 100644 index 0000000..a237b2c --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db56b6b413bcee8a28b47c27760a389b41b82cdecd72265a7ee37e199473c34 +size 13549812672 diff --git a/mistralai_Voxtral-Small-24B-2507-Q5_K_L.gguf b/mistralai_Voxtral-Small-24B-2507-Q5_K_L.gguf new file mode 100644 index 0000000..d81b427 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350b909423e912219c845642fd82e1656332af35a64edd3ecf2aeaeb0b70294a +size 17178704832 diff --git a/mistralai_Voxtral-Small-24B-2507-Q5_K_M.gguf b/mistralai_Voxtral-Small-24B-2507-Q5_K_M.gguf new file mode 100644 index 0000000..c6d98bc --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796e97c837e59065165efae6580cfa9ef68c505f3a4a0f861dc13af6f86aad78 +size 16764517312 diff --git a/mistralai_Voxtral-Small-24B-2507-Q5_K_S.gguf b/mistralai_Voxtral-Small-24B-2507-Q5_K_S.gguf new file mode 100644 index 0000000..fafa437 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271c32666c5af9140568bff2c34ba8c6ffe95a7b24fbc3875f77662c0bb017c5 +size 16304946112 diff --git a/mistralai_Voxtral-Small-24B-2507-Q6_K.gguf b/mistralai_Voxtral-Small-24B-2507-Q6_K.gguf new file mode 100644 index 0000000..986f92b --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b1c1be783c1162d3988a1c37355d0636bfb502ec055376318d18f13a4ba366f +size 19346471872 diff --git a/mistralai_Voxtral-Small-24B-2507-Q6_K_L.gguf b/mistralai_Voxtral-Small-24B-2507-Q6_K_L.gguf new file mode 100644 index 0000000..ac4045d --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff68862fcbc604be492c650f7b357ee12312e573f2c8faf4e12d6d3b2bc1a816 +size 19671530432 diff --git a/mistralai_Voxtral-Small-24B-2507-Q8_0.gguf b/mistralai_Voxtral-Small-24B-2507-Q8_0.gguf new file mode 100644 index 0000000..4651fd2 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8946691675152a7f96a7a098991387ac1cf3aa126b3def56114cbdd15b12b20 +size 25055312832 diff --git a/mistralai_Voxtral-Small-24B-2507-bf16.gguf b/mistralai_Voxtral-Small-24B-2507-bf16.gguf new file mode 100644 index 0000000..b2b129f --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ff6c30e8b7f863ad7b80093a7cbb60b890a39f576360359bb2da9dcac97896 +size 47154051744 diff --git a/mistralai_Voxtral-Small-24B-2507-imatrix.gguf b/mistralai_Voxtral-Small-24B-2507-imatrix.gguf new file mode 100644 index 0000000..7ee4ad8 --- /dev/null +++ b/mistralai_Voxtral-Small-24B-2507-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3872cc18522de658c9308673e5856e474683d4383e6b5829ff151259f84c4cec +size 10037344 diff --git a/mmproj-mistralai_Voxtral-Small-24B-2507-bf16.gguf b/mmproj-mistralai_Voxtral-Small-24B-2507-bf16.gguf new file mode 100644 index 0000000..818ed91 --- /dev/null +++ b/mmproj-mistralai_Voxtral-Small-24B-2507-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ded6ac855e722ed29b81286bbead477edbbfad3aba06e558c9261b699471d113 +size 1383657472 diff --git a/mmproj-mistralai_Voxtral-Small-24B-2507-f16.gguf b/mmproj-mistralai_Voxtral-Small-24B-2507-f16.gguf new file mode 100644 index 0000000..a9a5111 --- /dev/null +++ b/mmproj-mistralai_Voxtral-Small-24B-2507-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47fffe1beda0de1781e4602a9ec293e8fe8e722c5aabb640cf1abc57d8fbc681 +size 1383657472