commit 8fb059fab89204452d8af543229cc9e1f46b667c Author: ModelHub XC Date: Thu May 28 12:56:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e670174 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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-VL-4B-Thinking-FT-SFT.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-4B-Thinking-FT-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_M.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..841db8e --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cdb46c262c8bbc28007f218f684355a3fa8462138670ed9e94c2c8912a38d68 +size 1127020416 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_S.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..829e3a5 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2fb8087698e82bdd680e5d1564811d6ad65e28d95b1d7ab369653909566b07 +size 1055258496 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_M.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..bfc14b3 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a9e24c3185dbf4b528203483903ba869fbb0400a6e27349423072d2cb710918 +size 1512986496 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_S.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..f450d36 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44dc286a0aaaff19e39b088ef5488ab54a4fd581f80a088ed2dc67a78a7f5b56 +size 1417303936 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XS.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e1613d6 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672e5b1a8adc289b4d889fa1239d97682b652f3f525567ae53ce79c8e08e03fb +size 1354102656 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XXS.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..68929cf --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c955153545a8f45458af669ef7b7b74db85d3111a103c8e3d357347228aa3b81 +size 1246623616 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_M.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..5164549 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb5e2ccbb25025f15966febbde301e1418cf40078829dc4ba8ed99d51c1b55b +size 1962898816 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_S.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..9499e20 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cf4df8e5f5922b1c948bd26dc2e33d3dfa0d39b1857c0e709a6518a700f046 +size 1899533696 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XS.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..fb57de8 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd89600bfa2cfca986ec52f430238ba53b9547421281a16752ac00469aac0ae6 +size 1814377856 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XXS.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a12f9b1 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a50dd7817cbac415d82315f39234c306820b191d1fc3df4b17ba57ce494b0f +size 1670190976 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_NL.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..cfa2989 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccb31650562d7ba778202cee5b6fccda49d4578d133b8c44a6419226ff3d73a +size 2381346176 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_XS.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8466626 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0be59c7c60d8c917a158b07f054fd92060903d83d500fbd62140887cd872b60 +size 2270754176 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K.gguf new file mode 100644 index 0000000..8119635 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b306eb97d24055ada3fa235e0932e3c5fd69d8ee1503fcaa4ae2dd56cede3baf +size 1669502336 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K_S.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..492c117 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c01cc5310efe44e0d89aa4e19a90bf98ff34969fcee3e95630ab8bc2dde05a44 +size 1563456896 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_L.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e5510c9 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9599b758f528984dbdc3e94840ac5296471511a775408ef2edea84e4429461e6 +size 2239788416 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_M.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d0172bc --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2543a79d1a472fc8303a0043f59d31ae8ee4cf7ff4d719b91270daa5317a6980 +size 2075620736 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_S.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e10df43 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6da4a8948de0fb7d7c60f6fccafec0a2887920756572ca57df192cd80ab8c7 +size 1886999936 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_0.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_0.gguf new file mode 100644 index 0000000..264d269 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f36ebcf4b2bb2b738552c2adfbad94c6eb476cd4385a285739e12867b4ccf61e +size 2375775616 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_1.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_1.gguf new file mode 100644 index 0000000..e09d467 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c25516147a7f429fc7df90de5c2a3323a301182237630a15a66cfaff1cdc78e +size 2596631936 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_M.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..5fe0067 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0df25d7dbe9aa730007caa5e10759d126cabdd0750a5ad8427f62e2f0702696 +size 2497283456 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_S.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..7489c24 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c004e8b6f886d2f2270d92054273c1c10146983fa08231793d1f60b43f159d97 +size 2383312256 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_M.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..531004d --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c366c3f6c5c676e14f9bfa07df843c9c43d371062116929d78663be9ee209e4 +size 2889516416 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_S.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3194f70 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365d165cec49cc54bdab1416a5f359af08ea222fb8cb9cfee203a14483653f4d +size 2823714176 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q6_K.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q6_K.gguf new file mode 100644 index 0000000..427adb9 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9061400ed51e27bb58300b713a98de4f12871d1d430aa22e340ee8563e0a5401 +size 3306263936 diff --git a/Qwen3-VL-4B-Thinking-FT-SFT.imatrix.gguf b/Qwen3-VL-4B-Thinking-FT-SFT.imatrix.gguf new file mode 100644 index 0000000..8ef5072 --- /dev/null +++ b/Qwen3-VL-4B-Thinking-FT-SFT.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7ef8b701a3ca3fb429678f287347216e8926e3bb436e60e172a0df97f3402b +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7349e21 --- /dev/null +++ b/README.md @@ -0,0 +1,102 @@ +--- +base_model: aifeifei798/Qwen3-VL-4B-Thinking-FT-SFT +datasets: +- TeichAI/gemini-3-pro-preview-high-reasoning-250x +- TeichAI/gemini-3-pro-preview-high-reasoning-1000x +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- fragmented-training +- chain-of-thought +- reasoning +- qwen +- qwen3 +- cot +- dynamic-inference +- experimental +- sft +- unsloth +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/aifeifei798/Qwen3-VL-4B-Thinking-FT-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-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-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-4B-Thinking-FT-SFT-i1-GGUF/resolve/main/Qwen3-VL-4B-Thinking-FT-SFT.i1-Q6_K.gguf) | i1-Q6_K | 3.4 | 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. + +