commit b89cfd0e3ed8f189b49c39711b9845f39293b306 Author: ModelHub XC Date: Fri Jun 5 07:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7ca44d7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Qwen3-30B-A3B-Thinking-2507-FT.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_M.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_M.gguf new file mode 100644 index 0000000..69f1a1c --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddfa084e1692b506befd6f0f0c69d9f9bcf70aabc6bc817e26697b111397e869 +size 7078292736 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_S.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_S.gguf new file mode 100644 index 0000000..3b55c51 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0d87b6a55d5a0c61c4c6c180fe564af00a46e6d75786415217d088aadc52097 +size 6416510208 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_M.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_M.gguf new file mode 100644 index 0000000..cb87b46 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ef00a0739b52aca7fe4a0dcb5f556576549985283bdcc3b64b4c5ba2df893b +size 10169509120 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_S.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_S.gguf new file mode 100644 index 0000000..dae6f76 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2e73f8d0e044b218162b51788edae6d7cc630149e54f199d75c685b78749caf +size 9287132416 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XS.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..686927e --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa8dca351c753161f5e0fcc26727f878f6124113c29cb19edec58dc4c186b94 +size 9076223232 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XXS.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4ef4741 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60e5f9857bcda62b60ce71327b4632cc84a2ed5bb3abf7e0acedb806912813d +size 8181263616 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_M.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_M.gguf new file mode 100644 index 0000000..06ffe17 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b5f26ff5204c8d00bd1369193b64c21bfd208599ce9a96f7477f3b27d0c3717 +size 13513063680 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_S.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_S.gguf new file mode 100644 index 0000000..1b680e0 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85dfa1fd4912768117118df01982e41ca02d72e8a5ef0332798cf269b139893b +size 13299154176 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XS.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..53d3015 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c4d674b8185f1751592bb2749d668a365e4676544bb523dd15c04cb3d46e8c3 +size 12598443264 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XXS.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..de73b97 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ae87b30ed6bee1ea9dd11040e44fa7503e84b9b580e12c15260d7cbd5ef87b8 +size 11849327872 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ4_XS.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..96cd9a0 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261a6b297668d2332f4494bfb420c32c3c69e1e2670b470fdbd8c8efb72a6536 +size 16368350464 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K.gguf new file mode 100644 index 0000000..77aa1b7 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d13cc2194808492bfcb883370ba53c17ed8d32764d76b06230854f758b5e3b3 +size 11258610944 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K_S.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..dcfbf93 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2621d9eb2332ada73fe328571aabec7259689d1dede8dae978cef8edb087fddb +size 10519364864 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_L.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e176af5 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9afe1e0e392437b0f03d799e2e992b9e356a0b734b2ec04b161e45ef51e4d5b +size 15900671232 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_M.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..7445f34 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a110dbf2758451be2fc2d40f19f965a13d5976ca0fa65db8659b5986ed567b4 +size 14711848192 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_S.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7b34150 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08eafbc1cd671c74a0d4bf287b81c93712ef3f94befa4e5b9efd9667e9271b59 +size 13292469504 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_0.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_0.gguf new file mode 100644 index 0000000..d27c988 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab10477693aebf3b87a15fe4507f78a3560d34ab9db51b6e3f808ce289cec3f7 +size 17379988736 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_1.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_1.gguf new file mode 100644 index 0000000..ad8dd5f --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda30073487a5c35e67a25c0c8bab2e3315e3035394babaa8ff7d1244d950a8d +size 19192501504 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_M.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4c74aae --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:274ef7440208e33af882e06002b0c41d773968d683abc0d9bb615db672270694 +size 18556687616 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_S.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..69a157d --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e7bcb8006b7d428a70af5410b6992ea2ba12ac24baa92f2bef445cdcaf67ef +size 17456010496 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_M.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..5401e9c --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aec5e0fea293de1bc041a85e22ae763a13f447d56d8d6a360ccb919b9d61886 +size 21725582592 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_S.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..acb8cb9 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5116801361a1dce869aaa74fafa250715a6f61924e18d90ff9d757cc87f263d +size 21080511744 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q6_K.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q6_K.gguf new file mode 100644 index 0000000..39f6200 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c820d883801014214d1b85fbcd729fa479993f0d0c6563dac183c1aeeffbe9d9 +size 25092533504 diff --git a/Qwen3-30B-A3B-Thinking-2507-FT.imatrix.gguf b/Qwen3-30B-A3B-Thinking-2507-FT.imatrix.gguf new file mode 100644 index 0000000..d3fed47 --- /dev/null +++ b/Qwen3-30B-A3B-Thinking-2507-FT.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b7789ced4870f3d633dd03359fb95d4703ce1efd5f51fbd5155ae619b3e2d5e +size 122029312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..883dbaa --- /dev/null +++ b/README.md @@ -0,0 +1,96 @@ +--- +base_model: aifeifei798/Qwen3-30B-A3B-Thinking-2507-FT +datasets: +- TeichAI/gemini-3-pro-preview-high-reasoning-250x +language: +- zh +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen +- qwen3 +- unsloth +- Fragmented Training +- FT +- chat +- lora +- QiMing-Janus +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/aifeifei798/Qwen3-30B-A3B-Thinking-2507-FT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-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/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_S.gguf) | i1-IQ1_S | 6.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ1_M.gguf) | i1-IQ1_M | 7.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_S.gguf) | i1-IQ2_S | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ2_M.gguf) | i1-IQ2_M | 10.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q2_K.gguf) | i1-Q2_K | 11.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 11.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 13.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_S.gguf) | i1-IQ3_S | 13.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ3_M.gguf) | i1-IQ3_M | 13.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 14.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 16.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_0.gguf) | i1-Q4_0 | 17.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q4_1.gguf) | i1-Q4_1 | 19.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 21.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 21.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-30B-A3B-Thinking-2507-FT-i1-GGUF/resolve/main/Qwen3-30B-A3B-Thinking-2507-FT.i1-Q6_K.gguf) | i1-Q6_K | 25.2 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +