commit 0edeb653beb3dd40cf372019976d37d3ec3e5608 Author: ModelHub XC Date: Wed Jun 10 19:52:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6e9643f --- /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 +GPT-5-Distill-Qwen3-8B-conversation.f16.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-5-Distill-Qwen3-8B-conversation.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GPT-5-Distill-Qwen3-8B-conversation.IQ4_XS.gguf b/GPT-5-Distill-Qwen3-8B-conversation.IQ4_XS.gguf new file mode 100644 index 0000000..5251dff --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a8ee7bee5c6949189b6778e27fd0a5350b773ca7c58cd6fe583ae637b8c3aa +size 4593295552 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q2_K.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q2_K.gguf new file mode 100644 index 0000000..6d03b99 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c794f3a6e3163143d5b904d7be7ab93e0d3b657b7dfae6ef9cdd016dcccf8470 +size 3281731776 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_L.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_L.gguf new file mode 100644 index 0000000..5c83311 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58d3fbb4f6986eed72d99b2f8af1f6953f8b98963e5353158dc2e8d3bbba076 +size 4431392960 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_M.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_M.gguf new file mode 100644 index 0000000..36da1c1 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566bfb2a43a3eb4983e59a74b2c743eae9d1d135dffb73f665b7623d00ff25d1 +size 4124160192 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_S.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_S.gguf new file mode 100644 index 0000000..ab52ea7 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72bc6a71de9fff8d626d3df541ac9fdd886d82311b33ac7324c4323bbcd5aabf +size 3769610432 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q4_K_M.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q4_K_M.gguf new file mode 100644 index 0000000..74395d5 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8414b21b5e1872e075893111e9b34060d391f49766ee59c9dc47e028a58cec4 +size 5027782848 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q4_K_S.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q4_K_S.gguf new file mode 100644 index 0000000..4ebe3c0 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da21d2a6b3401805e963a53d32955c275101059de01837e62796813c51411c84 +size 4802011328 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q5_K_M.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q5_K_M.gguf new file mode 100644 index 0000000..d636376 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b18ec5006f50de85ee86c1af2ba33e04dcdb3d1cabaadc22381d2514bba93a20 +size 5851111616 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q5_K_S.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q5_K_S.gguf new file mode 100644 index 0000000..5e34004 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ff3ead684329b1da49f178b872a8f7810cc05e642a084e289cd6009295ad5a +size 5720760512 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q6_K.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q6_K.gguf new file mode 100644 index 0000000..6a57788 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e06e3a21eec8bab4e07ad8b4dddc6280a2182aed3091b96d7c39d4b76f8e85ed +size 6725898432 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.Q8_0.gguf b/GPT-5-Distill-Qwen3-8B-conversation.Q8_0.gguf new file mode 100644 index 0000000..c0a20d9 --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278f1a190864605edca566a573b2e3a35956975cc3868315199938b5143920e1 +size 8709517504 diff --git a/GPT-5-Distill-Qwen3-8B-conversation.f16.gguf b/GPT-5-Distill-Qwen3-8B-conversation.f16.gguf new file mode 100644 index 0000000..6d8176e --- /dev/null +++ b/GPT-5-Distill-Qwen3-8B-conversation.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a669589b8aa249863d24a2521468b67f8f5f3e21f63fcf56775540ec33d9e96 +size 16388042944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..04f46e8 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Jackrong/GPT-5-Distill-Qwen3-8B-conversation +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jackrong/GPT-5-Distill-Qwen3-8B-conversation + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GPT-5-Distill-Qwen3-8B-conversation-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/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-5-Distill-Qwen3-8B-conversation-GGUF/resolve/main/GPT-5-Distill-Qwen3-8B-conversation.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. + +