commit 4dc876d3aec80b1788a42141ef91668693674d46 Author: ModelHub XC Date: Sat Oct 31 21:00:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Qwen3-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4040d08 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen3_0.6B.F32.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3_0.6B.BF16.gguf b/Qwen3_0.6B.BF16.gguf new file mode 100644 index 0000000..d3074fc --- /dev/null +++ b/Qwen3_0.6B.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40157f5850ce1563dba644ba3a22ba857fe04a22c61b0c88a9c42b0af7ca0b3b +size 1198182560 diff --git a/Qwen3_0.6B.F16.gguf b/Qwen3_0.6B.F16.gguf new file mode 100644 index 0000000..fc3674c --- /dev/null +++ b/Qwen3_0.6B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7a7ef50546446e624bd33cf4113b2b3f26bc47bc3c0f6eeefa132a60b0e96f +size 1198182560 diff --git a/Qwen3_0.6B.F32.gguf b/Qwen3_0.6B.F32.gguf new file mode 100644 index 0000000..8c6cd7e --- /dev/null +++ b/Qwen3_0.6B.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb142fd95e6201c7d859bf7b17b78220ffeb5315552e0cb907523d64c11ce7e +size 2390151328 diff --git a/Qwen3_0.6B.Q3_K_M.gguf b/Qwen3_0.6B.Q3_K_M.gguf new file mode 100644 index 0000000..499b6b8 --- /dev/null +++ b/Qwen3_0.6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3842f5a51f5021e0bd87c2cf72c8870d0219347c4b80140186b3591aa382239 +size 347126944 diff --git a/Qwen3_0.6B.Q3_K_S.gguf b/Qwen3_0.6B.Q3_K_S.gguf new file mode 100644 index 0000000..b637d6f --- /dev/null +++ b/Qwen3_0.6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8a17d46e425540fef66cd27b4423baddb4b9610180699b6888cb40625be4aec +size 323075232 diff --git a/Qwen3_0.6B.Q4_K_M.gguf b/Qwen3_0.6B.Q4_K_M.gguf new file mode 100644 index 0000000..bcb7f26 --- /dev/null +++ b/Qwen3_0.6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2883b98c1396be553c252b27382cae54baad12b4087e6bec86af024bd412afa9 +size 396704928 diff --git a/Qwen3_0.6B.Q4_K_S.gguf b/Qwen3_0.6B.Q4_K_S.gguf new file mode 100644 index 0000000..eff5dfa --- /dev/null +++ b/Qwen3_0.6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e5156a6909e1b962bd71051752e7a062185756b30d9994fd9bfeb487f084ea2 +size 383270048 diff --git a/Qwen3_0.6B.Q5_K_M.gguf b/Qwen3_0.6B.Q5_K_M.gguf new file mode 100644 index 0000000..5937c63 --- /dev/null +++ b/Qwen3_0.6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f5ba7d72bcc7ef6ac7093cd18ba25e23aa59770e15a5c36d4cc0b0b38ef199e +size 444415136 diff --git a/Qwen3_0.6B.Q8_0.gguf b/Qwen3_0.6B.Q8_0.gguf new file mode 100644 index 0000000..292ad62 --- /dev/null +++ b/Qwen3_0.6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3146bab54e4632678c1e306fd475ad500eae1f2d2c06255205799152892f3bf6 +size 639447200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f1c2fbe --- /dev/null +++ b/README.md @@ -0,0 +1,57 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Qwen/Qwen3-0.6B +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +- moe +--- + +# **Qwen3-0.6B-GGUF** + +> Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support + +## Model Files + +| File Name | Size | Quantization | Format | Description | +| ------------------------ | ------- | ------------ | ------ | -------------------------------- | +| `Qwen3_0.6B.F32.gguf` | 2.39 GB | FP32 | GGUF | Full precision (float32) version | +| `Qwen3_0.6B.BF16.gguf` | 1.2 GB | BF16 | GGUF | BFloat16 precision version | +| `Qwen3_0.6B.F16.gguf` | 1.2 GB | FP16 | GGUF | Float16 precision version | +| `Qwen3_0.6B.Q3_K_M.gguf` | 347 MB | Q3\_K\_M | GGUF | 3-bit quantized (K M variant) | +| `Qwen3_0.6B.Q3_K_S.gguf` | 323 MB | Q3\_K\_S | GGUF | 3-bit quantized (K S variant) | +| `Qwen3_0.6B.Q4_K_M.gguf` | 397 MB | Q4\_K\_M | GGUF | 4-bit quantized (K M variant) | +| `Qwen3_0.6B.Q4_K_S.gguf` | 383 MB | Q4\_K\_S | GGUF | 4-bit quantized (K S variant) | +| `Qwen3_0.6B.Q5_K_M.gguf` | 444 MB | Q5\_K\_M | GGUF | 5-bit quantized (K M variant) | +| `Qwen3_0.6B.Q8_0.gguf` | 639 MB | Q8\_0 | GGUF | 8-bit quantized | +| `.gitattributes` | 2.04 kB | — | — | Git LFS tracking file | +| `config.json` | 31 B | — | — | Configuration placeholder | +| `README.md` | 3.53 kB | — | — | Model documentation | + +## Quants Usage + +(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/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.f16.gguf) | f16 | 1.6 | 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) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..d1b8b99 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen3" +} \ No newline at end of file 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