commit 2e0edd58a05c6de8f4e84308d6d799c2ce68a538 Author: ModelHub XC Date: Tue Jul 21 01:36:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-TerminalBench-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..67db34c --- /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 +Qwen3-4B-TerminalBench.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-TerminalBench.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-TerminalBench.IQ4_XS.gguf b/Qwen3-4B-TerminalBench.IQ4_XS.gguf new file mode 100644 index 0000000..bc14716 --- /dev/null +++ b/Qwen3-4B-TerminalBench.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3689ce203b806d85953d2508bb1f650cdc07a41d497b59fa18b299c733d50a1e +size 2286317280 diff --git a/Qwen3-4B-TerminalBench.Q2_K.gguf b/Qwen3-4B-TerminalBench.Q2_K.gguf new file mode 100644 index 0000000..365b099 --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d9abca3c7a857582bd3593a87e5cf38e54f8da7b5de25e8a1f5159ee061021 +size 1669500640 diff --git a/Qwen3-4B-TerminalBench.Q3_K_L.gguf b/Qwen3-4B-TerminalBench.Q3_K_L.gguf new file mode 100644 index 0000000..c87e36c --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a2c41a00bf02518a4c70be3efd94df17153a6cca1461899f270b4529423cbcc +size 2239786720 diff --git a/Qwen3-4B-TerminalBench.Q3_K_M.gguf b/Qwen3-4B-TerminalBench.Q3_K_M.gguf new file mode 100644 index 0000000..91ac713 --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b2bd5eb63c068a9804b7ae00fb1d1d793023efcef1e4b53019123e35fa8fd29 +size 2075619040 diff --git a/Qwen3-4B-TerminalBench.Q3_K_S.gguf b/Qwen3-4B-TerminalBench.Q3_K_S.gguf new file mode 100644 index 0000000..69258a4 --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92f001a86770ef6b8d295f124b86b275e4b6e91f01674562ba0c2eb919bee40f +size 1886998240 diff --git a/Qwen3-4B-TerminalBench.Q4_K_M.gguf b/Qwen3-4B-TerminalBench.Q4_K_M.gguf new file mode 100644 index 0000000..48b40f4 --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a3e6647771bbf7b85d267c204b1e67ee3cb561d16bdce95bef84db5d6a319d +size 2497281760 diff --git a/Qwen3-4B-TerminalBench.Q4_K_S.gguf b/Qwen3-4B-TerminalBench.Q4_K_S.gguf new file mode 100644 index 0000000..27e9dee --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4acb73366326c5c0cb97d694c7b87fbdb4caa0501e3ca66527de5de776111a +size 2383310560 diff --git a/Qwen3-4B-TerminalBench.Q5_K_M.gguf b/Qwen3-4B-TerminalBench.Q5_K_M.gguf new file mode 100644 index 0000000..ce97342 --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db94761f6e1fce3018f6f8a1fe66b11e1768c76ccf3e354f0de0044af24fae50 +size 2889514720 diff --git a/Qwen3-4B-TerminalBench.Q5_K_S.gguf b/Qwen3-4B-TerminalBench.Q5_K_S.gguf new file mode 100644 index 0000000..e3be67d --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:652a3d24c9cbf2e8661d47d8274492993a97629c74c60f07bd4ae2214880a1b9 +size 2823712480 diff --git a/Qwen3-4B-TerminalBench.Q6_K.gguf b/Qwen3-4B-TerminalBench.Q6_K.gguf new file mode 100644 index 0000000..aa9d3b4 --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d6d862a306c7e036e00e74f6f6ab0f13e1e0143189ab532e042c00c762e586 +size 3306262240 diff --git a/Qwen3-4B-TerminalBench.Q8_0.gguf b/Qwen3-4B-TerminalBench.Q8_0.gguf new file mode 100644 index 0000000..e93ab85 --- /dev/null +++ b/Qwen3-4B-TerminalBench.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:802d171b371817079b80aae3d616845e3a7817e60d07375ffce1da6a936f647b +size 4280406240 diff --git a/Qwen3-4B-TerminalBench.f16.gguf b/Qwen3-4B-TerminalBench.f16.gguf new file mode 100644 index 0000000..d7742d0 --- /dev/null +++ b/Qwen3-4B-TerminalBench.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb6098498f912017497c39711a18f07265624f47bb5d222ecbafc0a6c77818f1 +size 8051286240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..85a5593 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: prometheus04/Qwen3-4B-TerminalBench +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/prometheus04/Qwen3-4B-TerminalBench + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-TerminalBench-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/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-TerminalBench-GGUF/resolve/main/Qwen3-4B-TerminalBench.f16.gguf) | f16 | 8.2 | 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. + +