commit d63cab626fb168c9554c0f05765cfaf245f2eaeb Author: ModelHub XC Date: Thu May 7 16:58:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7049fac --- /dev/null +++ b/.gitattributes @@ -0,0 +1,62 @@ +*.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 +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf filter=lfs diff=lfs merge=lfs -text +XiaomiMiMo_MiMo-VL-7B-SFT-2508-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-XiaomiMiMo_MiMo-VL-7B-SFT-2508-f16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa455d7 --- /dev/null +++ b/README.md @@ -0,0 +1,164 @@ +--- +quantized_by: bartowski +pipeline_tag: image-text-to-text +base_model_relation: quantized +base_model: XiaomiMiMo/MiMo-VL-7B-SFT-2508 +--- + +## Llamacpp imatrix Quantizations of MiMo-VL-7B-SFT-2508 by XiaomiMiMo + +Using llama.cpp release b6317 for quantization. + +Original model: https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-SFT-2508 + +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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [MiMo-VL-7B-SFT-2508-bf16.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf) | bf16 | 15.25GB | false | Full BF16 weights. | +| [MiMo-VL-7B-SFT-2508-Q8_0.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q8_0.gguf) | Q8_0 | 8.11GB | false | Extremely high quality, generally unneeded but max available quant. | +| [MiMo-VL-7B-SFT-2508-Q6_K_L.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K_L.gguf) | Q6_K_L | 6.56GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q6_K.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K.gguf) | Q6_K | 6.26GB | false | Very high quality, near perfect, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q5_K_L.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_L.gguf) | Q5_K_L | 5.83GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q5_K_M.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_M.gguf) | Q5_K_M | 5.45GB | false | High quality, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q5_K_S.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_S.gguf) | Q5_K_S | 5.33GB | false | High quality, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q4_K_L.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_L.gguf) | Q4_K_L | 5.15GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q4_1.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_1.gguf) | Q4_1 | 4.89GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [MiMo-VL-7B-SFT-2508-Q4_K_M.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q3_K_XL.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_XL.gguf) | Q3_K_XL | 4.68GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [MiMo-VL-7B-SFT-2508-Q4_K_S.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_S.gguf) | Q4_K_S | 4.48GB | false | Slightly lower quality with more space savings, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q4_0.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_0.gguf) | Q4_0 | 4.47GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [MiMo-VL-7B-SFT-2508-IQ4_NL.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_NL.gguf) | IQ4_NL | 4.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [MiMo-VL-7B-SFT-2508-IQ4_XS.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_XS.gguf) | IQ4_XS | 4.26GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [MiMo-VL-7B-SFT-2508-Q3_K_L.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_L.gguf) | Q3_K_L | 4.14GB | false | Lower quality but usable, good for low RAM availability. | +| [MiMo-VL-7B-SFT-2508-Q3_K_M.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_M.gguf) | Q3_K_M | 3.85GB | false | Low quality. | +| [MiMo-VL-7B-SFT-2508-Q2_K_L.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K_L.gguf) | Q2_K_L | 3.68GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [MiMo-VL-7B-SFT-2508-IQ3_M.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_M.gguf) | IQ3_M | 3.65GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [MiMo-VL-7B-SFT-2508-Q3_K_S.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_S.gguf) | Q3_K_S | 3.53GB | false | Low quality, not recommended. | +| [MiMo-VL-7B-SFT-2508-IQ3_XS.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XS.gguf) | IQ3_XS | 3.40GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [MiMo-VL-7B-SFT-2508-IQ3_XXS.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XXS.gguf) | IQ3_XXS | 3.15GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [MiMo-VL-7B-SFT-2508-Q2_K.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K.gguf) | Q2_K | 3.08GB | false | Very low quality but surprisingly usable. | +| [MiMo-VL-7B-SFT-2508-IQ2_M.gguf](https://huggingface.co/bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF/blob/main/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ2_M.gguf) | IQ2_M | 2.87GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF --include "XiaomiMiMo_MiMo-VL-7B-SFT-2508-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/XiaomiMiMo_MiMo-VL-7B-SFT-2508-GGUF --include "XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (XiaomiMiMo_MiMo-VL-7B-SFT-2508-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/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ2_M.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ2_M.gguf new file mode 100644 index 0000000..71e62df --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcee424a0adb4254fc1739173f9b12c42371abe79a7fc7d02f87b67047fd1de7 +size 2867920320 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_M.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_M.gguf new file mode 100644 index 0000000..3862511 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14d90c0d8532cd675faad7cfba9ded55eea69ff0f7618a1811a1908a8d0abf3 +size 3650063808 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XS.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XS.gguf new file mode 100644 index 0000000..625c8e9 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac2f9029b6650682ed6b15f123e52418c39693c33b8a5e88448fd0124e01d71 +size 3396373952 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XXS.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XXS.gguf new file mode 100644 index 0000000..68a845c --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee916cd221128b3b5101d206f285007a7468a5225eba82f47364885e9b218954 +size 3152543168 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_NL.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_NL.gguf new file mode 100644 index 0000000..148d445 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:814632f6019e38779c1ec8eed97013650313e032aac5b565ac736830169af031 +size 4474510784 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_XS.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_XS.gguf new file mode 100644 index 0000000..19a18fb --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91bfa0f6d12c63f0504392ffff134839d0060afca646dfbf13ee68e6dce6f6e +size 4260453824 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K.gguf new file mode 100644 index 0000000..759f20c --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1672ad62ae750fff40423992fddf441ce32abb119b4bb906e8538cf67197f76 +size 3076406720 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K_L.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K_L.gguf new file mode 100644 index 0000000..4d94616 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81bfedb8e5ac5cdb8ea829ce28b9c375a8f5ce63e472135972012cd303a61d89 +size 3683126720 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_L.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_L.gguf new file mode 100644 index 0000000..f5b8f9d --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba737e0595087902b30fca2b1d9b8ce649f312600557023bac5c977d751e441a +size 4138962368 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_M.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_M.gguf new file mode 100644 index 0000000..b3a10df --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e77978bef94afdafebcf9db17ae7dfc25a9065f65d282530c15fb269132936 +size 3854011840 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_S.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_S.gguf new file mode 100644 index 0000000..726e4f6 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deef5cc6fd5b0a87a40324c0cfed10ed8c35805d49471d51c54fffc59de22a43 +size 3525840320 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_XL.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_XL.gguf new file mode 100644 index 0000000..d8ef9ee --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b1a1e47e132948805299a8c73bd41e298512ac220412ab8a18c20a29f49066 +size 4682583488 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_0.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_0.gguf new file mode 100644 index 0000000..65a6aa7 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9c81be7093f14edd2f8fa20246691d0c048fe57d01e62d49f712b996cf8055 +size 4466908608 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_1.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_1.gguf new file mode 100644 index 0000000..d460e55 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa58b2487914e35b5f63c74b8817a4fbb6dcbdbe14ba6f693ed1993474f7db00 +size 4893187520 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_L.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_L.gguf new file mode 100644 index 0000000..5d77465 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29dea6de719710080fde5de676a553409fde11771952817a307ed41baced357b +size 5145447872 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_M.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_M.gguf new file mode 100644 index 0000000..ace2cca --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8047ffa0ea97897661b0c300e41b35da64ce023fd3ea518b219fc11e9b2906 +size 4684340672 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_S.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_S.gguf new file mode 100644 index 0000000..aa9c0d3 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fb09366bb8c3b5e7f9a447a714c30b1ef432c9028d95b46225bfdf500e917e +size 4480277952 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_L.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_L.gguf new file mode 100644 index 0000000..276f3e8 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:809ffbebe6f94afc3d258b570f71c3f57b05b88d80c73a9423865fffe634fffc +size 5832003008 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_M.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_M.gguf new file mode 100644 index 0000000..5d2c351 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b9c22d7b1c5d315f229364cfe6e8c2ec66fef468e196539afe8035d2023378 +size 5448555968 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_S.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_S.gguf new file mode 100644 index 0000000..5023029 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7c6e1daaf9c386808bb1980a74ec6c469eccac9d7d662746a6832da7742940 +size 5330738624 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K.gguf new file mode 100644 index 0000000..ad00c58 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90235db52916cbdfba2ae3894b365ce0ceaefb7ae1d158ab28137af912b7906e +size 6260534720 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K_L.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K_L.gguf new file mode 100644 index 0000000..e936f9d --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc450e2058cb2e1539a2a5d776de658f1c411daf6c42c8fe08181e7798843a5 +size 6561467840 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q8_0.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q8_0.gguf new file mode 100644 index 0000000..d39a765 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fc786570b75444e96530bcd95e30da65852467b423fcd1f380ffefe5facc40c +size 8106511808 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf new file mode 100644 index 0000000..6458a52 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01c5fe29c17a7f055f6deee9bda327eba3d70df1290a3ecbbd732b98850ce899 +size 15252229280 diff --git a/XiaomiMiMo_MiMo-VL-7B-SFT-2508-imatrix.gguf b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-imatrix.gguf new file mode 100644 index 0000000..a188f52 --- /dev/null +++ b/XiaomiMiMo_MiMo-VL-7B-SFT-2508-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf1e22ca1cb5455926632c2ef04c7e3a1483124e444422841f2bfe4645da7c4 +size 5162880 diff --git a/mmproj-XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf b/mmproj-XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf new file mode 100644 index 0000000..335755b --- /dev/null +++ b/mmproj-XiaomiMiMo_MiMo-VL-7B-SFT-2508-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47672440b4df1a80620748409bedd65c3d7077ed8219f63371af9bca3df53db +size 1371274400 diff --git a/mmproj-XiaomiMiMo_MiMo-VL-7B-SFT-2508-f16.gguf b/mmproj-XiaomiMiMo_MiMo-VL-7B-SFT-2508-f16.gguf new file mode 100644 index 0000000..8f70874 --- /dev/null +++ b/mmproj-XiaomiMiMo_MiMo-VL-7B-SFT-2508-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df246a4b88206b8c35ca829f1932479551a6be07c1ff1796fb8cace208c23da8 +size 1368263840