commit ecd0a128bfb8b8e88efba6255588241c9942dada Author: ModelHub XC Date: Mon Oct 19 17:16:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/mistralai_Magistral-Small-2506-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c3f5df2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +*.gguf* 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-2506.imatrix 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..652124a --- /dev/null +++ b/README.md @@ -0,0 +1,200 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +extra_gated_description: If you want to learn more about how we process your personal + data, please read our Privacy Policy. +license: apache-2.0 +inference: false +language: +- en +- fr +- de +- es +- pt +- it +- ja +- ko +- ru +- zh +- ar +- fa +- id +- ms +- ne +- pl +- ro +- sr +- sv +- tr +- uk +- vi +- hi +- bn +base_model: mistralai/Magistral-Small-2506 +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Magistral-Small-2506 by mistralai + +**Thank you to mlx-community for uploading a BF16 version with proper tokenizer config [here](https://huggingface.co/mlx-community/Magistral-Small-2506-bf16)** + +Using llama.cpp release b5596 for quantization. + +Original model: https://huggingface.co/mistralai/Magistral-Small-2506 + +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 + +``` +[SYSTEM_PROMPT]{system_prompt}[/SYSTEM_PROMPT][INST]{prompt}[/INST] +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Magistral-Small-2506-bf16.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-bf16.gguf) | bf16 | 47.15GB | false | Full BF16 weights. | +| [Magistral-Small-2506-Q8_0.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q8_0.gguf) | Q8_0 | 25.05GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Magistral-Small-2506-Q6_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-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-2506-Q6_K.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q6_K.gguf) | Q6_K | 19.35GB | false | Very high quality, near perfect, *recommended*. | +| [Magistral-Small-2506-Q5_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q5_K_L.gguf) | Q5_K_L | 17.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Magistral-Small-2506-Q5_K_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q5_K_M.gguf) | Q5_K_M | 16.76GB | false | High quality, *recommended*. | +| [Magistral-Small-2506-Q5_K_S.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q5_K_S.gguf) | Q5_K_S | 16.30GB | false | High quality, *recommended*. | +| [Magistral-Small-2506-Q4_1.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-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-2506-Q4_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q4_K_L.gguf) | Q4_K_L | 14.83GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Magistral-Small-2506-Q4_K_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q4_K_M.gguf) | Q4_K_M | 14.33GB | false | Good quality, default size for most use cases, *recommended*. | +| [Magistral-Small-2506-Q4_K_S.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q4_K_S.gguf) | Q4_K_S | 13.55GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Magistral-Small-2506-Q4_0.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q4_0.gguf) | Q4_0 | 13.49GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Magistral-Small-2506-IQ4_NL.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-IQ4_NL.gguf) | IQ4_NL | 13.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Magistral-Small-2506-Q3_K_XL.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-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-2506-IQ4_XS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-IQ4_XS.gguf) | IQ4_XS | 12.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Magistral-Small-2506-Q3_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q3_K_L.gguf) | Q3_K_L | 12.40GB | false | Lower quality but usable, good for low RAM availability. | +| [Magistral-Small-2506-Q3_K_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q3_K_M.gguf) | Q3_K_M | 11.47GB | false | Low quality. | +| [Magistral-Small-2506-IQ3_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-IQ3_M.gguf) | IQ3_M | 10.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Magistral-Small-2506-Q3_K_S.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q3_K_S.gguf) | Q3_K_S | 10.40GB | false | Low quality, not recommended. | +| [Magistral-Small-2506-IQ3_XS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-IQ3_XS.gguf) | IQ3_XS | 9.91GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Magistral-Small-2506-Q2_K_L.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-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-2506-IQ3_XXS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-IQ3_XXS.gguf) | IQ3_XXS | 9.28GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Magistral-Small-2506-Q2_K.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-Q2_K.gguf) | Q2_K | 8.89GB | false | Very low quality but surprisingly usable. | +| [Magistral-Small-2506-IQ2_M.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-IQ2_M.gguf) | IQ2_M | 8.11GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | +| [Magistral-Small-2506-IQ2_S.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-IQ2_S.gguf) | IQ2_S | 7.48GB | false | Low quality, uses SOTA techniques to be usable. | +| [Magistral-Small-2506-IQ2_XS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-IQ2_XS.gguf) | IQ2_XS | 7.21GB | false | Low quality, uses SOTA techniques to be usable. | +| [Magistral-Small-2506-IQ2_XXS.gguf](https://huggingface.co/bartowski/mistralai_Magistral-Small-2506-GGUF/blob/main/mistralai_Magistral-Small-2506-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-2506-GGUF --include "mistralai_Magistral-Small-2506-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-2506-GGUF --include "mistralai_Magistral-Small-2506-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (mistralai_Magistral-Small-2506-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/mistralai_Magistral-Small-2506-IQ2_M.gguf b/mistralai_Magistral-Small-2506-IQ2_M.gguf new file mode 100644 index 0000000..8e53569 --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d49ec6e9868212798b8c48928fff0f5a6182a7d5ddec9d47338b6ae43b7694ce +size 8114052960 diff --git a/mistralai_Magistral-Small-2506-IQ2_S.gguf b/mistralai_Magistral-Small-2506-IQ2_S.gguf new file mode 100644 index 0000000..59b0d20 --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bcfcc4ed998133966cbe15ef9935ca1c1e6efe891ac4f571a397fb2e59538bf +size 7478353760 diff --git a/mistralai_Magistral-Small-2506-IQ2_XS.gguf b/mistralai_Magistral-Small-2506-IQ2_XS.gguf new file mode 100644 index 0000000..ed29f30 --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f26f8227f4a8a17b6f9cd9c712f384c8282772bb6139dcb3ce5fb64677c848 +size 7207034720 diff --git a/mistralai_Magistral-Small-2506-IQ2_XXS.gguf b/mistralai_Magistral-Small-2506-IQ2_XXS.gguf new file mode 100644 index 0000000..4ba991c --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ae6cc039b0eebb11b2c2e076d4ea02d0f4151e5effa5de1d770640518f5e84 +size 6545121120 diff --git a/mistralai_Magistral-Small-2506-IQ3_M.gguf b/mistralai_Magistral-Small-2506-IQ3_M.gguf new file mode 100644 index 0000000..f9f741d --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13405ed96eefde29a8c82c89c9abbbc0d363ec30d924080ef8c43cf42a4f7ea8 +size 10650951520 diff --git a/mistralai_Magistral-Small-2506-IQ3_XS.gguf b/mistralai_Magistral-Small-2506-IQ3_XS.gguf new file mode 100644 index 0000000..731ba2e --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91982e439508cabac357195fe91ba4956a85972d104b1b3a0dc38e0a1fc182d2 +size 9907117920 diff --git a/mistralai_Magistral-Small-2506-IQ3_XXS.gguf b/mistralai_Magistral-Small-2506-IQ3_XXS.gguf new file mode 100644 index 0000000..60c7fbe --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2be8532d0bdc1ad75e90c69a2612dca8852e85f39b43b79e029d548f5f6797 +size 9280593760 diff --git a/mistralai_Magistral-Small-2506-IQ4_NL.gguf b/mistralai_Magistral-Small-2506-IQ4_NL.gguf new file mode 100644 index 0000000..3441a6a --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66005b9598ee8fab6631a873a15214e195a2a9afac8c9be8b3b67fdb9a214ca +size 13468016480 diff --git a/mistralai_Magistral-Small-2506-IQ4_XS.gguf b/mistralai_Magistral-Small-2506-IQ4_XS.gguf new file mode 100644 index 0000000..6e31a83 --- /dev/null +++ b/mistralai_Magistral-Small-2506-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66d49ad28813ba7b42f48ad040ed5ce8cfdc0683a5261189cad7ae416949aa7 +size 12758916960 diff --git a/mistralai_Magistral-Small-2506-Q2_K.gguf b/mistralai_Magistral-Small-2506-Q2_K.gguf new file mode 100644 index 0000000..03791a8 --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426f545ad0508b675994e7b96326c48f6180be918957923ce81e8f1fd7301f50 +size 8890326880 diff --git a/mistralai_Magistral-Small-2506-Q2_K_L.gguf b/mistralai_Magistral-Small-2506-Q2_K_L.gguf new file mode 100644 index 0000000..f3eab85 --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07a42ceb30d4c97690a53038dac981f7cd03771b8622f3f0ffeddb6b1ee61d58 +size 9545686880 diff --git a/mistralai_Magistral-Small-2506-Q3_K_L.gguf b/mistralai_Magistral-Small-2506-Q3_K_L.gguf new file mode 100644 index 0000000..79e522d --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec5919761001b1c6a52af846cdf17edf5dc1f0f3ab8927e9490f3fbc4992dc1 +size 12400762720 diff --git a/mistralai_Magistral-Small-2506-Q3_K_M.gguf b/mistralai_Magistral-Small-2506-Q3_K_M.gguf new file mode 100644 index 0000000..89c0502 --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fab714d82031342823b38dfa4f33ca3b8d53a87f88802bc46dd99f66308067a1 +size 11474083680 diff --git a/mistralai_Magistral-Small-2506-Q3_K_S.gguf b/mistralai_Magistral-Small-2506-Q3_K_S.gguf new file mode 100644 index 0000000..9068bda --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2311d219cab64714aba29d9d6928a367a0fb17440651e4a02915a7d5936f38e2 +size 10400276320 diff --git a/mistralai_Magistral-Small-2506-Q3_K_XL.gguf b/mistralai_Magistral-Small-2506-Q3_K_XL.gguf new file mode 100644 index 0000000..9adb19d --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de721ce2079ff2139ce36bb84aa31f77e491ae66e950c9f4e345a3bb5d3f00b2 +size 12987965280 diff --git a/mistralai_Magistral-Small-2506-Q4_0.gguf b/mistralai_Magistral-Small-2506-Q4_0.gguf new file mode 100644 index 0000000..862a965 --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8767c4216d6c62f01c649a5fcc82aa62648bb04c3041187069545895159e124c +size 13494230880 diff --git a/mistralai_Magistral-Small-2506-Q4_1.gguf b/mistralai_Magistral-Small-2506-Q4_1.gguf new file mode 100644 index 0000000..2a3cb9a --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c725e90c0bf0183983564b7c14d17aea3ae2528f78f373f726144175059643a +size 14873108320 diff --git a/mistralai_Magistral-Small-2506-Q4_K_L.gguf b/mistralai_Magistral-Small-2506-Q4_K_L.gguf new file mode 100644 index 0000000..f53dc9c --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fbeab608888908a447e0d11051d185aab79a84a025bc43c4c2a03da0d6ddad1 +size 14831984480 diff --git a/mistralai_Magistral-Small-2506-Q4_K_M.gguf b/mistralai_Magistral-Small-2506-Q4_K_M.gguf new file mode 100644 index 0000000..8d3416d --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b681b81ba30238b7654db77b4b3afa7b0f6226c84d8bbd5a5dfb1a5a3cb95816 +size 14333910880 diff --git a/mistralai_Magistral-Small-2506-Q4_K_S.gguf b/mistralai_Magistral-Small-2506-Q4_K_S.gguf new file mode 100644 index 0000000..e619c4d --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97409e2a10f71f0acb87abcc2ba72a0e5aab0173b6de1c2f10c4b9cbe397ebb +size 13549281120 diff --git a/mistralai_Magistral-Small-2506-Q5_K_L.gguf b/mistralai_Magistral-Small-2506-Q5_K_L.gguf new file mode 100644 index 0000000..b532b4f --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f59d56ed06a9b5d8e5aee87700e46aef16e27bb9204ca48d0d963eee85a609a +size 17178173280 diff --git a/mistralai_Magistral-Small-2506-Q5_K_M.gguf b/mistralai_Magistral-Small-2506-Q5_K_M.gguf new file mode 100644 index 0000000..117506d --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b74dfcdf9e46eaf0bc47d43d0c88314a1e7e5ecf2fd0cf74be7f9882b5ee9b70 +size 16763985760 diff --git a/mistralai_Magistral-Small-2506-Q5_K_S.gguf b/mistralai_Magistral-Small-2506-Q5_K_S.gguf new file mode 100644 index 0000000..708b1ef --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aacba20c977195acf881ef94adacaf85b58e7f59cfc031f8471d7d6ca06d74c9 +size 16304414560 diff --git a/mistralai_Magistral-Small-2506-Q6_K.gguf b/mistralai_Magistral-Small-2506-Q6_K.gguf new file mode 100644 index 0000000..2486203 --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60c3ce30b4c045fe0fbd6762072f258217a857fd995ce559386c6e1aa240802 +size 19345940320 diff --git a/mistralai_Magistral-Small-2506-Q6_K_L.gguf b/mistralai_Magistral-Small-2506-Q6_K_L.gguf new file mode 100644 index 0000000..8e63a89 --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663748ef04f8bd56e2816c410a6bc7476278496365a14c040eb273483761c743 +size 19670998880 diff --git a/mistralai_Magistral-Small-2506-Q8_0.gguf b/mistralai_Magistral-Small-2506-Q8_0.gguf new file mode 100644 index 0000000..e888cb7 --- /dev/null +++ b/mistralai_Magistral-Small-2506-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5fd7eff278de98232bf62973bc6c7d8a516eea7af0942bca55609c338fc52c +size 25054781280 diff --git a/mistralai_Magistral-Small-2506-bf16.gguf b/mistralai_Magistral-Small-2506-bf16.gguf new file mode 100644 index 0000000..594e4c2 --- /dev/null +++ b/mistralai_Magistral-Small-2506-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ddab04611da48923c5e910d8763714c72f504152dbaa51abe42bebe23a9515 +size 47153520192 diff --git a/mistralai_Magistral-Small-2506.imatrix b/mistralai_Magistral-Small-2506.imatrix new file mode 100644 index 0000000..1485832 --- /dev/null +++ b/mistralai_Magistral-Small-2506.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f5f6e675b7e390888183d5f4d6b18cfd262caa029808d02b722ddbf3f0f7ab9 +size 10003538