commit 9cd54017383e985c0cd15197a0c3f01ff08903df Author: ModelHub XC Date: Sat Jul 18 02:36:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-4B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c658e0 --- /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 +Qwen1.5-4B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-4B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-4B-Chat.IQ4_XS.gguf b/Qwen1.5-4B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..5369444 --- /dev/null +++ b/Qwen1.5-4B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:446f075609015666f8658e5118aeb9714221b5045e98d452fbbf191b3df38399 +size 2232632448 diff --git a/Qwen1.5-4B-Chat.Q2_K.gguf b/Qwen1.5-4B-Chat.Q2_K.gguf new file mode 100644 index 0000000..fe786d5 --- /dev/null +++ b/Qwen1.5-4B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd033070df0f4f8a850b210f0b78be854ba48fd272e79744a9e93412caefa394 +size 1620633728 diff --git a/Qwen1.5-4B-Chat.Q3_K_L.gguf b/Qwen1.5-4B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..4d7fba6 --- /dev/null +++ b/Qwen1.5-4B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c239e8382e493a91a71a7e6328ab4928e78242dc90ef37fdb4aac5c380b1348c +size 2174799488 diff --git a/Qwen1.5-4B-Chat.Q3_K_M.gguf b/Qwen1.5-4B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..7188a14 --- /dev/null +++ b/Qwen1.5-4B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e8b2b79c5b28576d99579679729ddbb648e9cebb5d0a07a676a2fce104e7ccd +size 2026851968 diff --git a/Qwen1.5-4B-Chat.Q3_K_S.gguf b/Qwen1.5-4B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..f7b6d96 --- /dev/null +++ b/Qwen1.5-4B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90635c6b36d3f37216526ea94292590d010b6b5f2ae1d7e4a5a3a470a0f3163a +size 1857154688 diff --git a/Qwen1.5-4B-Chat.Q4_K_M.gguf b/Qwen1.5-4B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..e75df1e --- /dev/null +++ b/Qwen1.5-4B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfcfd1c88dc393b96696983cdc31495dfaa186d6398306ce872bcebf0d0011af +size 2455116928 diff --git a/Qwen1.5-4B-Chat.Q4_K_S.gguf b/Qwen1.5-4B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..4f0087a --- /dev/null +++ b/Qwen1.5-4B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ffc8074bf5d55a5610c44f6156908e5561e5fee0bb9aaafb1226e8723f0ac0 +size 2344422528 diff --git a/Qwen1.5-4B-Chat.Q5_K_M.gguf b/Qwen1.5-4B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..2bfdcac --- /dev/null +++ b/Qwen1.5-4B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10104ecc85c462247f205f7a6146d37daf00d121bf1d64ab73195bdf495d442d +size 2839608448 diff --git a/Qwen1.5-4B-Chat.Q5_K_S.gguf b/Qwen1.5-4B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..951add3 --- /dev/null +++ b/Qwen1.5-4B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baba89170d71c9d03c96300b67ce2db9764e5be97b22ef9009dec520700eab52 +size 2775198848 diff --git a/Qwen1.5-4B-Chat.Q6_K.gguf b/Qwen1.5-4B-Chat.Q6_K.gguf new file mode 100644 index 0000000..2d84f10 --- /dev/null +++ b/Qwen1.5-4B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2446c09d04ef3cbab2b8e2caf6d4235acb2a1405d14a5a4d410bc65ae8f85502 +size 3248130688 diff --git a/Qwen1.5-4B-Chat.Q8_0.gguf b/Qwen1.5-4B-Chat.Q8_0.gguf new file mode 100644 index 0000000..cb7eedd --- /dev/null +++ b/Qwen1.5-4B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70976f46ec5c8ad262c5a0c4579cb8ce17164a0a2206e426c522d62793e2b758 +size 4204736128 diff --git a/Qwen1.5-4B-Chat.f16.gguf b/Qwen1.5-4B-Chat.f16.gguf new file mode 100644 index 0000000..96d7814 --- /dev/null +++ b/Qwen1.5-4B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aee109cfc93604e8d38099fd2972ade2f91ddef543a6e960f842791f9f3f181 +size 7907724928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c00d7c4 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Qwen/Qwen1.5-4B-Chat +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen1.5-4B-Chat/blob/main/LICENSE +license_name: tongyi-qianwen-research +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen1.5-4B-Chat + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen1.5-4B-Chat-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-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/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q2_K.gguf) | Q2_K | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.IQ4_XS.gguf) | IQ4_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q4_K_S.gguf) | Q4_K_S | 2.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.Q8_0.gguf) | Q8_0 | 4.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-4B-Chat-GGUF/resolve/main/Qwen1.5-4B-Chat.f16.gguf) | f16 | 8.0 | 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. + +