commit 07d1c27b26e89f6684ccf29894044ed61012b24e Author: ModelHub XC Date: Sun Aug 2 20:11:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e492901 --- /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 + +deepseek-ai_DeepSeek-R1-0528-Qwen3-8B.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..3e7488d --- /dev/null +++ b/README.md @@ -0,0 +1,167 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B +license: mit +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of DeepSeek-R1-0528-Qwen3-8B by deepseek-ai + +Using llama.cpp release b5524 for quantization. + +Original model: https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B + +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 + +``` +<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜> +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [DeepSeek-R1-0528-Qwen3-8B-bf16.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. | +| [DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. | +| [DeepSeek-R1-0528-Qwen3-8B-Q6_K_L.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q5_K_L.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q4_K_L.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q4_1.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_XL.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_XL.gguf) | Q3_K_XL | 4.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [DeepSeek-R1-0528-Qwen3-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [DeepSeek-R1-0528-Qwen3-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. | +| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. | +| [DeepSeek-R1-0528-Qwen3-8B-IQ3_M.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [DeepSeek-R1-0528-Qwen3-8B-Q2_K_L.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. | +| [DeepSeek-R1-0528-Qwen3-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [DeepSeek-R1-0528-Qwen3-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. | +| [DeepSeek-R1-0528-Qwen3-8B-IQ2_M.gguf](https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ2_M.gguf) | IQ2_M | 3.05GB | 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/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF --include "deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-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/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF --include "deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-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/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ2_M.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ2_M.gguf new file mode 100644 index 0000000..d85157c --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aaa12ea8ffa4a8ed3702af0a07e6f0422ba9252625e56d64d41c9415495d717 +size 3051913600 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_M.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_M.gguf new file mode 100644 index 0000000..7ac2ef9 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44259398b1ea4dd36f6e2147452d4f8d0feb6fc887a6c827d6f88c9e0f0a52c +size 3896619392 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_XS.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_XS.gguf new file mode 100644 index 0000000..2a4f286 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bab013ec073cba291d32353e46d7e1a4c9e9e5a01567886fd8ad13d78ce5025 +size 3626873216 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_XXS.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_XXS.gguf new file mode 100644 index 0000000..84811d2 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d963159f643e881e6c80cb8c77cba70cc580d5eddb06c58bcb7828f1cd3bae9 +size 3369632128 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ4_NL.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ4_NL.gguf new file mode 100644 index 0000000..7414cd2 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:884de7279fd8e9d80f01c0ec9ec8a48ad8b988d91a79e871f78e0b7ec133425d +size 4793622912 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ4_XS.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ4_XS.gguf new file mode 100644 index 0000000..6855ab2 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3ed47e622d5d331d251069814fc45745637242715306641766946fc8de4940 +size 4561838464 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf new file mode 100644 index 0000000..5b00944 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe2029c5978581b980cdcbad06febe663447586783b8d884ad8c238b5f047bd +size 3281731968 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q2_K_L.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q2_K_L.gguf new file mode 100644 index 0000000..664e816 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af04458dbfbac80e31d43a832d401c30a7f13b5de5ffd685aa7a4aefd2e4c696 +size 3889475968 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf new file mode 100644 index 0000000..715e6bd --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd9a3010a2918f45001d760d2790cd01145db5af00f8e5fffcc18c2b8e4fcaf +size 4431393152 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf new file mode 100644 index 0000000..a3fc643 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f30d347c42b347d39cb46a17acf4945fa1c9f795b0b07f876bef5298a139f1 +size 4124160384 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf new file mode 100644 index 0000000..c51447e --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04a1a72e4bd5dd6add80423de05a4b07d6f1bd08af033f3b901816ea892d110 +size 3769610624 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_XL.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_XL.gguf new file mode 100644 index 0000000..6cddc56 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50cc544b43e2d7bb5d203f9e2763c3b6c73b7862283e73eec25d3b3595a93269 +size 4975931776 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf new file mode 100644 index 0000000..d102a5d --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71a983c64eb72a2b4a885993cd0675474afe7e92d72b051ab8716b23157daa0 +size 4787331456 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_1.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_1.gguf new file mode 100644 index 0000000..263624d --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a1546a120de793ae79465331e1dbab335c0c3f096f5587d0c381f8398e8a25 +size 5247754624 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_L.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_L.gguf new file mode 100644 index 0000000..9051bc2 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ddf1b2707b269ec15dfb90c0aa71f478a381c19b5fb1715e219e0529415b2d4 +size 5489668480 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf new file mode 100644 index 0000000..654d6f5 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c2f118fd59f3a16f20d18b0e7f79e960c84bc8c66d94fd71a691e05151d54f +size 5027783040 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf new file mode 100644 index 0000000..07bf152 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203945c0afc1e526febf712d122671fa44ee95b57201d4cf0b37edd6261758fe +size 4802011520 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_L.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_L.gguf new file mode 100644 index 0000000..c0a92fa --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fae68eac5bb977f061558bc7c1bdc17cfb2a8b53494c14eaf753007a3b1d7421 +size 6235206016 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf new file mode 100644 index 0000000..f8b1d35 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5842a7d03f76cf11a418447ef63f12750dc340430ac8a330a6faa8fe8ddc8040 +size 5851111808 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf new file mode 100644 index 0000000..4b869b9 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6df7ee66a970ed3fca16e90c18f0b8da43cb09ccf44bb9da51ed38654f79fb5 +size 5720760704 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf new file mode 100644 index 0000000..c4f3870 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bbe05d4279f4f84de9ca6d1756ffc080a17cec6e0b8f99853480b199a559785 +size 6725898624 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q6_K_L.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q6_K_L.gguf new file mode 100644 index 0000000..8e24083 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179354d7da8054c50197dadb736e6b800c47064c10b6bdeb0a3a791cee33c6ae +size 7027339648 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf new file mode 100644 index 0000000..de133d3 --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9144694fd6a4347d9842b20797946754fb673871b92ba966e32e51b9057fa428 +size 8709517696 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-bf16.gguf b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-bf16.gguf new file mode 100644 index 0000000..101616f --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cba24c93e99fbf5e752ac72ffc3777abc3dacd5de4c8044bce047d460c54c11b +size 16388042816 diff --git a/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B.imatrix b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B.imatrix new file mode 100644 index 0000000..1a454bb --- /dev/null +++ b/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f07a101ef6afeee4ae633f3b936163f6ca9b1c8881d4ce02b18ef38655982ef +size 5316782