commit 4a8be25d1a4d876641d307c48c8f241c5a2ff3db Author: ModelHub XC Date: Mon Apr 20 11:19:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2928b9e --- /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 +Qwen-3-4b-Z-Prompter-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-3-4b-Z-Prompter-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-3-4b-Z-Prompter-v1.IQ4_XS.gguf b/Qwen-3-4b-Z-Prompter-v1.IQ4_XS.gguf new file mode 100644 index 0000000..e93bead --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7c582a6ffdf3e9df6fcad35a56a6a314c423ad95671a60db9fd5eb1331f62c8 +size 2286316704 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q2_K.gguf b/Qwen-3-4b-Z-Prompter-v1.Q2_K.gguf new file mode 100644 index 0000000..c69715a --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6776e1d1482dd03e703f5b133180dba1a126733f5564e3d1522f12253241a5a +size 1669500064 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q3_K_L.gguf b/Qwen-3-4b-Z-Prompter-v1.Q3_K_L.gguf new file mode 100644 index 0000000..f8f8996 --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4ed68241c843eff31d41acc0fbcd2d48efb592766c20f8f6db0f9b8a8809a64 +size 2239786144 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q3_K_M.gguf b/Qwen-3-4b-Z-Prompter-v1.Q3_K_M.gguf new file mode 100644 index 0000000..5c3af6d --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8648ed5bdadd541371e2c237a624218dddfd52c0f7aa16990a152fc9a21b9aff +size 2075618464 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q3_K_S.gguf b/Qwen-3-4b-Z-Prompter-v1.Q3_K_S.gguf new file mode 100644 index 0000000..3d09777 --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:058c5f69fd2e30c39f4e0ccbd2fcde2eeb926c7c5df9980be5bc12f59c04a897 +size 1886997664 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q4_K_M.gguf b/Qwen-3-4b-Z-Prompter-v1.Q4_K_M.gguf new file mode 100644 index 0000000..af84de3 --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5927b69ef3503c78aa3947f950fbfe9fe6234484b8251ec6398e25fbb9d5b9a8 +size 2497281184 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q4_K_S.gguf b/Qwen-3-4b-Z-Prompter-v1.Q4_K_S.gguf new file mode 100644 index 0000000..03a73cb --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e89f4f7082ff5809922cd43fd95662921ae5434fc8da4f9c892745d3b16cb29 +size 2383309984 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q5_K_M.gguf b/Qwen-3-4b-Z-Prompter-v1.Q5_K_M.gguf new file mode 100644 index 0000000..3365ef7 --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2424406760480b2dfe9760a20cdb8be45f3f190d7c72c8607a6d3ca7dc75b7 +size 2889514144 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q5_K_S.gguf b/Qwen-3-4b-Z-Prompter-v1.Q5_K_S.gguf new file mode 100644 index 0000000..0aa7a35 --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68092dbc30946a4aec016a8ca885cec11fb4dfe3314f19518e9f1668c65189a5 +size 2823711904 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q6_K.gguf b/Qwen-3-4b-Z-Prompter-v1.Q6_K.gguf new file mode 100644 index 0000000..547b95e --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b586a7701eaf7b1d92bb0d9183ea233db5d5093342eaa2f6e455a88e16e00a53 +size 3306261664 diff --git a/Qwen-3-4b-Z-Prompter-v1.Q8_0.gguf b/Qwen-3-4b-Z-Prompter-v1.Q8_0.gguf new file mode 100644 index 0000000..3e159d1 --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0528fb1c7e2a9abafcaf80154adf5f493a05f6d4aff16d8e0261e31093cbaefd +size 4280405664 diff --git a/Qwen-3-4b-Z-Prompter-v1.f16.gguf b/Qwen-3-4b-Z-Prompter-v1.f16.gguf new file mode 100644 index 0000000..c7c97a2 --- /dev/null +++ b/Qwen-3-4b-Z-Prompter-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3247c8874fa1b13c46f140063f00a16d01fc5e2dbdcf38d8d68d7cbb05254782 +size 8051285664 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1e595bd --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: CalmState/Qwen-3-4b-Z-Prompter-v1 +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/CalmState/Qwen-3-4b-Z-Prompter-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-3-4b-Z-Prompter-v1-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/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-3-4b-Z-Prompter-v1-GGUF/resolve/main/Qwen-3-4b-Z-Prompter-v1.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. + +