commit 41108bc9fc5c0ddc5352d42f6d02364d1e871907 Author: ModelHub XC Date: Tue Jun 2 01:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a195369 --- /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 +SiliconMind-V1-Qwen3-4B-T-2507-76k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SiliconMind-V1-Qwen3-4B-T-2507-76k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e71ecdf --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: AS-SiliconMind/SiliconMind-V1-Qwen3-4B-T-2507-76k +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/AS-SiliconMind/SiliconMind-V1-Qwen3-4B-T-2507-76k/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- verilog +- reasoning +- multi-agent +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AS-SiliconMind/SiliconMind-V1-Qwen3-4B-T-2507-76k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SiliconMind-V1-Qwen3-4B-T-2507-76k-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/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SiliconMind-V1-Qwen3-4B-T-2507-76k-GGUF/resolve/main/SiliconMind-V1-Qwen3-4B-T-2507-76k.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. + + diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.IQ4_XS.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.IQ4_XS.gguf new file mode 100644 index 0000000..f180a0c --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eac0a73c2cd82a63d40de70a55671cb86bef37a940d2b3bbfc049500d54e4a40 +size 2286316992 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q2_K.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q2_K.gguf new file mode 100644 index 0000000..a138e84 --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14475f09ca2b3d427d1558a402dd6f23851f4b0ce1067a265103ecbc4eb9df1d +size 1669500352 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_L.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_L.gguf new file mode 100644 index 0000000..198e9c6 --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84b14d28d6ee572264bb556842f521d2e3dff2e669d089caf08792c3266b7720 +size 2239786432 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_M.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_M.gguf new file mode 100644 index 0000000..71ea11a --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c01db7f3ea4f08aa306f3f9a1122b5f22caf94a901624e4d1a614691ae31de +size 2075618752 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_S.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_S.gguf new file mode 100644 index 0000000..dc27db3 --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64b97b43eecf760d0900ff02d84bcd50a8eb1530b3c1d53c043d2046f562b05f +size 1886997952 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_M.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_M.gguf new file mode 100644 index 0000000..e777aa2 --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd00b04e16875b507aec60e3a67c5d8f3d53c97ec10eb9ff7cbc8e2f034308c +size 2497281472 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_S.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_S.gguf new file mode 100644 index 0000000..10ac096 --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26968d13d21334d24b2dda02c5146b1addd006167840c74d76083fb329a0280 +size 2383310272 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_M.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_M.gguf new file mode 100644 index 0000000..d0945eb --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7459789aec82c10d081801ff628f5ee878218d13ce313b40ff93bc8f78bf9485 +size 2889514432 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_S.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_S.gguf new file mode 100644 index 0000000..a14f73b --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f8e8cb05018826aff08530073198af7bc2231182745c31f427bf6374150f025 +size 2823712192 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q6_K.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q6_K.gguf new file mode 100644 index 0000000..1b36cfd --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d5a5c3ac6ebc2fbfc5da28e2ea4af9edd89db12195f0bb213eb266819b18ec +size 3306261952 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q8_0.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q8_0.gguf new file mode 100644 index 0000000..c34f00a --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a96e284932055ce957e996a38f5a2e2f752a6833c28655930727c3b7b0cb349 +size 4280405952 diff --git a/SiliconMind-V1-Qwen3-4B-T-2507-76k.f16.gguf b/SiliconMind-V1-Qwen3-4B-T-2507-76k.f16.gguf new file mode 100644 index 0000000..96f8345 --- /dev/null +++ b/SiliconMind-V1-Qwen3-4B-T-2507-76k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad899d406b20be57bb5b9e600f18220338752042558b72ed4fcb41741a323463 +size 8051285952