commit 34d63638681a4ad4498c586c26d4b301b51270db Author: ModelHub XC Date: Tue Oct 13 18:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/huatuo_sft_qwen3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ebbc35c --- /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 +huatuo_sft_qwen3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +huatuo_sft_qwen3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f7b1bea --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: ReasoningEval/huatuo_sft_qwen3-8b +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ReasoningEval/huatuo_sft_qwen3-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#huatuo_sft_qwen3-8b-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_qwen3-8b.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/huatuo_sft_qwen3-8b-GGUF/resolve/main/huatuo_sft_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. + + diff --git a/huatuo_sft_qwen3-8b.IQ4_XS.gguf b/huatuo_sft_qwen3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..5c95bfa --- /dev/null +++ b/huatuo_sft_qwen3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2010442a2d3bdaca6b8617eba02ab4f16bc3b977645cf3646ce342ac3ba8247 +size 4593296608 diff --git a/huatuo_sft_qwen3-8b.Q2_K.gguf b/huatuo_sft_qwen3-8b.Q2_K.gguf new file mode 100644 index 0000000..3279c2c --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:615bf5a85d38a7f2edfbed9116863d87921053beef2214948108d19f4d6b9777 +size 3281732832 diff --git a/huatuo_sft_qwen3-8b.Q3_K_L.gguf b/huatuo_sft_qwen3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..5e7f2c9 --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4757b62757d18b5549e4884e990feffb777ea50092db5dde43987dadce16422b +size 4431394016 diff --git a/huatuo_sft_qwen3-8b.Q3_K_M.gguf b/huatuo_sft_qwen3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..acd3c2e --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c17404aab375d903fd318d9f9f675b41118412ec8098bd197d2f1b2d4a09911 +size 4124161248 diff --git a/huatuo_sft_qwen3-8b.Q3_K_S.gguf b/huatuo_sft_qwen3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..eded8d0 --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fba556884b3ad12c97c1d6c3df3e8d1618a600908027891e836eb9c9f9e439c +size 3769611488 diff --git a/huatuo_sft_qwen3-8b.Q4_K_M.gguf b/huatuo_sft_qwen3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..479390a --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f5091b9d3e1d96b493df01b3aa3f1e86ffc004fa6b920a8c13f22ea1fed565e +size 5027783904 diff --git a/huatuo_sft_qwen3-8b.Q4_K_S.gguf b/huatuo_sft_qwen3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..5dca7c6 --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:423027305d328f997aeefea9acc921ff62c0fa451c979313c3d4e9e6ed6fefd7 +size 4802012384 diff --git a/huatuo_sft_qwen3-8b.Q5_K_M.gguf b/huatuo_sft_qwen3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..688329f --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23648b249261722796193b34307a10823199dc4515cb3b85c98761a75a79729e +size 5851112672 diff --git a/huatuo_sft_qwen3-8b.Q5_K_S.gguf b/huatuo_sft_qwen3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..a668033 --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e53d206765a01bbdc4c0ed52801823f2d66d00eb12f8ac6dbe735f44ba9b7d5 +size 5720761568 diff --git a/huatuo_sft_qwen3-8b.Q6_K.gguf b/huatuo_sft_qwen3-8b.Q6_K.gguf new file mode 100644 index 0000000..ea8f576 --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:031e132d78674ad09678643806565f1acb74fab881869bffc6e0d8e33bd64289 +size 6725899488 diff --git a/huatuo_sft_qwen3-8b.Q8_0.gguf b/huatuo_sft_qwen3-8b.Q8_0.gguf new file mode 100644 index 0000000..48a4273 --- /dev/null +++ b/huatuo_sft_qwen3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9ab3d08a34d6efbebb43eec1ecd3204e5633ae3d3b297ad337f2f9d30463332 +size 8709518560 diff --git a/huatuo_sft_qwen3-8b.f16.gguf b/huatuo_sft_qwen3-8b.f16.gguf new file mode 100644 index 0000000..5424f9a --- /dev/null +++ b/huatuo_sft_qwen3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf10b34cbc7a5762b4c8efc0fc4059a23871c8daed51c14f6ecac9dc9392de20 +size 16388044000