commit 2b10f3b75ee083a59b8e13d42282725d7edce0de Author: ModelHub XC Date: Sat May 9 21:22:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4109acd --- /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-Thinking-2507-Esper3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Thinking-2507-Esper3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.IQ4_XS.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.IQ4_XS.gguf new file mode 100644 index 0000000..82b2fca --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536ed74a1d6c3cbd161f5237e70174cd124f84bb5f1bf19e11f713522cd5b6b1 +size 2286318528 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q2_K.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q2_K.gguf new file mode 100644 index 0000000..a80e836 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0941a93291c4c95c850549ceb96b1e8ba024b16dffc02c82da15be188444d1 +size 1669501888 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_L.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_L.gguf new file mode 100644 index 0000000..a44259f --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b7fcf88e4e1d5faf67160261e86d68690c6108737935f50ddadc4627454a4e +size 2239787968 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_M.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_M.gguf new file mode 100644 index 0000000..5592855 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9311501664ebfa133c4c1b0f85777220870d6bc4037b26331d03d41860b970 +size 2075620288 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_S.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_S.gguf new file mode 100644 index 0000000..d3ffd3a --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f272cf0a42de827c9b7205487ca307b156eafa418b24d3918508afd3e2610b4 +size 1886999488 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_M.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_M.gguf new file mode 100644 index 0000000..d7031cc --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b84fc7f0d4f1adc6ad14fcb232d74f2c5088df3e3d003841350911341875eb +size 2497283008 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_S.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_S.gguf new file mode 100644 index 0000000..17e2e40 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b73c11875e900929b2a0185c7fd53ba56207f310d76756266dbae069d5b81b9 +size 2383311808 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_M.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_M.gguf new file mode 100644 index 0000000..13dc027 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f46ad2f675c45f831d310e6b789bcade6530dcd7280612a800af49c9da55095 +size 2889515968 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_S.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_S.gguf new file mode 100644 index 0000000..e6ac264 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f57caf6d2c17335d4712802fc68d3ce3809b5026626ebce11677ee33cf74a761 +size 2823713728 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q6_K.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q6_K.gguf new file mode 100644 index 0000000..9b4669d --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c466d2e75061efc337c32c0580a01214fb9955577bfd361c3972da4db02a20a3 +size 3306263488 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.Q8_0.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.Q8_0.gguf new file mode 100644 index 0000000..2c5898b --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9781e8b5e2ddc5d0476d857942fa1a0c4258b245ccf48956d7413aed56ea9f20 +size 4280407488 diff --git a/Qwen3-4B-Thinking-2507-Esper3.1.f16.gguf b/Qwen3-4B-Thinking-2507-Esper3.1.f16.gguf new file mode 100644 index 0000000..e42bb35 --- /dev/null +++ b/Qwen3-4B-Thinking-2507-Esper3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d87ceb71bd4840375250e3a2459b69be4c2acaeaff1ab57b5198cc559f19748 +size 8051287488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..28b91af --- /dev/null +++ b/README.md @@ -0,0 +1,122 @@ +--- +base_model: ValiantLabs/Qwen3-4B-Thinking-2507-Esper3.1 +datasets: +- sequelbox/Titanium3-DeepSeek-V3.1-Terminus +- sequelbox/Tachibana3-Part1-DeepSeek-V3.1-Terminus +- sequelbox/Tachibana3-Part2-DeepSeek-V3.2 +- sequelbox/Mitakihara-DeepSeek-R1-0528 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- esper +- esper-3.1 +- esper-3 +- valiant +- valiant-labs +- qwen +- qwen-3 +- qwen-3-4b +- qwen3-4b-thinking-2507 +- 4b +- reasoning +- code +- code-instruct +- python +- javascript +- dev-ops +- jenkins +- terraform +- ansible +- docker +- jenkins +- kubernetes +- helm +- grafana +- prometheus +- shell +- bash +- azure +- aws +- gcp +- cloud +- scripting +- powershell +- problem-solving +- architect +- engineer +- developer +- creative +- analytical +- expert +- rationality +- conversational +- chat +- instruct +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ValiantLabs/Qwen3-4B-Thinking-2507-Esper3.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Thinking-2507-Esper3.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-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/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Thinking-2507-Esper3.1-GGUF/resolve/main/Qwen3-4B-Thinking-2507-Esper3.1.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. + +