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
2026-06-04 00:32:17 +08:00
commit 83570452d7
31 changed files with 317 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/README.md
+++ 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 <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b6014">b6014</a> 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
+
+<details>
+  <summary>Click to view download instructions</summary>
+
+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 (./)
+
+</details>
+
+## 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.
+
+<details>
+  <summary>Click to view Q4_0_X_X information (deprecated</summary>
+
+I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
+
+<details>
+  <summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
+
+| 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
+
+</details>
+
+</details>
+
+## Which file should I choose?
+
+<details>
+  <summary>Click here for details</summary>
+
+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.
+
+</details>
+
+## 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
--- a/mistralai_Voxtral-Small-24B-2507-IQ2_M.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-IQ2_S.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-IQ2_XS.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-IQ3_M.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-IQ3_XS.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-IQ3_XXS.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-IQ4_NL.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-IQ4_XS.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q2_K.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q2_K_L.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q3_K_L.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q3_K_M.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q3_K_S.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q3_K_XL.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q4_0.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q4_1.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q4_K_L.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q4_K_M.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q4_K_S.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q5_K_L.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q5_K_M.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q5_K_S.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q6_K.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q6_K_L.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-Q8_0.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-bf16.gguf
+++ 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
--- a/mistralai_Voxtral-Small-24B-2507-imatrix.gguf
+++ 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
--- a/mmproj-mistralai_Voxtral-Small-24B-2507-bf16.gguf
+++ 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
--- a/mmproj-mistralai_Voxtral-Small-24B-2507-f16.gguf
+++ 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