commit 3aab6d757447ed2e21c345f43a71df8d522c24e9 Author: ModelHub XC Date: Wed Jun 10 20:03:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..90faad1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +DeepSeek-R1-0528-Qwen3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-0528-Qwen3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-0528-Qwen3-8B.IQ4_XS.gguf b/DeepSeek-R1-0528-Qwen3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..8be2353 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46f14ee185a2466bee49a2d6cd68a51364f92d83fee1ebc4e4c2eb6e40d8ef6 +size 4593295904 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q2_K.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q2_K.gguf new file mode 100644 index 0000000..93b390f --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b9898d825cc3b5459b3a5357ac1c23a6a38eb40bc75174271b6018c6b401ad5 +size 3281732128 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q3_K_L.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0b3b1a2 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4521cd5d0ffd9911e75e5f8f7f936eb3b09e0b38b28bf35e42411f588075b64c +size 4431393312 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q3_K_M.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..1ccf0f2 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db3e92ac0c0540ba0d1544af3ba2c283eec7eb945a46676a69e4cf8112d1603 +size 4124160544 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q3_K_S.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..2c85157 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fba844a34e3f332f72ac6cbd73ec3c6e73029a58b09ec3c11862af6aa8f7303 +size 3769610784 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q4_K_M.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..9a5d41e --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f17c3f2cb45ab115155d2272b109ff4ac7951784cc76b4781de25ab0790007 +size 5027783200 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q4_K_S.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..58a5269 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b12b878da95a11296a6bb31dfc0c92694b5fad82ad24a0106b742f5ff8a6c6 +size 4802011680 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q5_K_M.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..266c26a --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db32cd750b28c5125051d36e738394a435c75497957c93868f8d3ad5ab5b748 +size 5851111968 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q5_K_S.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..c9ad7b0 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2d5adbc6ba2efc391b8ef6601470adb13a1ce30d409fbef6c152c5be6240be +size 5720760864 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q6_K.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q6_K.gguf new file mode 100644 index 0000000..9612091 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3df21a0a68fe694dfd633b637c147eb0f31a7c27e55afd5de0ac90e4cecd48 +size 6725898784 diff --git a/DeepSeek-R1-0528-Qwen3-8B.Q8_0.gguf b/DeepSeek-R1-0528-Qwen3-8B.Q8_0.gguf new file mode 100644 index 0000000..243c925 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3a615a4f94eafb59d8684fc9a7e909a4c69193737a5c1aaadf8cfd577e681e +size 8709517856 diff --git a/DeepSeek-R1-0528-Qwen3-8B.f16.gguf b/DeepSeek-R1-0528-Qwen3-8B.f16.gguf new file mode 100644 index 0000000..2cdb6e0 --- /dev/null +++ b/DeepSeek-R1-0528-Qwen3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ff2aebcac2f66a2073477498f4ef280eb2d7d9995432a4c873295b214897fe +size 16388043296 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b374472 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-R1-0528-Qwen3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/DeepSeek-R1-0528-Qwen3-8B.f16.gguf) | f16 | 16.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +