commit f54b52db4966f8bca4247ba0d749b30477efe297 Author: ModelHub XC Date: Wed May 20 18:34:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mio-Qwen3-4B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..958781f --- /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 +Mio-Qwen3-4B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mio-Qwen3-4B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mio-Qwen3-4B.i1-IQ1_M.gguf b/Mio-Qwen3-4B.i1-IQ1_M.gguf new file mode 100644 index 0000000..b1a4e92 --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:832594794cd34ecfe379e5010735286bb390c7dc8d0ae6fd75ff7113e8d69587 +size 1127017984 diff --git a/Mio-Qwen3-4B.i1-IQ1_S.gguf b/Mio-Qwen3-4B.i1-IQ1_S.gguf new file mode 100644 index 0000000..215c533 --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed576f443505916cfed65d181e9624b44f075a0e3072cd7d030bff5849eba63f +size 1055256064 diff --git a/Mio-Qwen3-4B.i1-IQ2_M.gguf b/Mio-Qwen3-4B.i1-IQ2_M.gguf new file mode 100644 index 0000000..4037a04 --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8293c9ae050ef4fb6a370243a3a41fec077e4ec29d5ceceaf45f5ecdcd2ec65 +size 1512984064 diff --git a/Mio-Qwen3-4B.i1-IQ2_S.gguf b/Mio-Qwen3-4B.i1-IQ2_S.gguf new file mode 100644 index 0000000..af8100f --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:102dc326d8f8bdf1f42dacf91b4d841523a13b9a5bdbc51c289cef895c95a31e +size 1417301504 diff --git a/Mio-Qwen3-4B.i1-IQ2_XS.gguf b/Mio-Qwen3-4B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..27b38f1 --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a061d867ee2d4b60d8d5de80054722f5229972ea048044bcdf0e7ed626169633 +size 1354100224 diff --git a/Mio-Qwen3-4B.i1-IQ2_XXS.gguf b/Mio-Qwen3-4B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..b3f67c1 --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbaeabfdbe0a3f5140ef5585a2bb4d1e17585d1334c9c542cb57fd585a14c227 +size 1246621184 diff --git a/Mio-Qwen3-4B.i1-IQ3_M.gguf b/Mio-Qwen3-4B.i1-IQ3_M.gguf new file mode 100644 index 0000000..e3b9921 --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1009e37be727af40155d3d81a82bd0c3f5251c2fa6a4fe0ab82c758bcd0289 +size 1962896384 diff --git a/Mio-Qwen3-4B.i1-IQ3_S.gguf b/Mio-Qwen3-4B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1f212e9 --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42d72379a755d94a114e90c75655641d87a79cb82c71492ea701d0c30e4168ee +size 1899531264 diff --git a/Mio-Qwen3-4B.i1-IQ3_XS.gguf b/Mio-Qwen3-4B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..615116f --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539060fa6e2a8676db50c4d8fb8e43e316adeca43e46247c52ada845e93609ba +size 1814375424 diff --git a/Mio-Qwen3-4B.i1-IQ3_XXS.gguf b/Mio-Qwen3-4B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e03519e --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be89839c35c2d55163a2f3b78bdf1221a4e43e6d7c3a07fa13764792b1345f1 +size 1670188544 diff --git a/Mio-Qwen3-4B.i1-IQ4_NL.gguf b/Mio-Qwen3-4B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..8a93c9e --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:293ff5620588f00dd4e61ff5f27f42f19f1602495a405704ee98070e397b0bc0 +size 2381343744 diff --git a/Mio-Qwen3-4B.i1-IQ4_XS.gguf b/Mio-Qwen3-4B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..811b1f9 --- /dev/null +++ b/Mio-Qwen3-4B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3590e4ee2e9179232f538dd54c65256dc2dd3e8777e4a0fa2aa2edd6378f9c74 +size 2270751744 diff --git a/Mio-Qwen3-4B.i1-Q2_K.gguf b/Mio-Qwen3-4B.i1-Q2_K.gguf new file mode 100644 index 0000000..f58b5c5 --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3da74ca852417cc28d5dc5fe0414da428349321ffcdabb1bcfa49a93275e48eb +size 1669499904 diff --git a/Mio-Qwen3-4B.i1-Q2_K_S.gguf b/Mio-Qwen3-4B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..faa98fc --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a46f18ec21bc706389f5bedecee7a9a72ff821df617660b0a95d1dae7e9951d +size 1563454464 diff --git a/Mio-Qwen3-4B.i1-Q3_K_L.gguf b/Mio-Qwen3-4B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1a611b1 --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1b32a1be3430986a782f8600a1113f393b3b4a4a0962eb74e88415a497c45e +size 2239785984 diff --git a/Mio-Qwen3-4B.i1-Q3_K_M.gguf b/Mio-Qwen3-4B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..5097d3d --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd299372a265db72be89a72505b2b46d9bd0aaee1eecf767d3281eb610811d4 +size 2075618304 diff --git a/Mio-Qwen3-4B.i1-Q3_K_S.gguf b/Mio-Qwen3-4B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..98ff282 --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caaeadb0cfda31236dc423ad509e73ef677171599c62781be505ca4389bb12d3 +size 1886997504 diff --git a/Mio-Qwen3-4B.i1-Q4_0.gguf b/Mio-Qwen3-4B.i1-Q4_0.gguf new file mode 100644 index 0000000..7fb485d --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700757256e96042fdc3e5d5514cf698e2d579eaa1f1b45de4adbfb7f947cf518 +size 2375773184 diff --git a/Mio-Qwen3-4B.i1-Q4_1.gguf b/Mio-Qwen3-4B.i1-Q4_1.gguf new file mode 100644 index 0000000..26a3f92 --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11cb888d184f88d65169f2140a8cd5d2f0885b58f6c5d35c2a85ba7d3447227 +size 2596629504 diff --git a/Mio-Qwen3-4B.i1-Q4_K_M.gguf b/Mio-Qwen3-4B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..570a0e0 --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:474ea665e6488d0c8eae7b11a622143191366b8f1259eff0ded239a81ed29676 +size 2497281024 diff --git a/Mio-Qwen3-4B.i1-Q4_K_S.gguf b/Mio-Qwen3-4B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fad46f1 --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1641658a414daba654a77943717daf12a1858155833432e5b829b550089de2 +size 2383309824 diff --git a/Mio-Qwen3-4B.i1-Q5_K_M.gguf b/Mio-Qwen3-4B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..9d98799 --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb72f86690bf52edb6b5afef2f6cc1778489aae7f84b5842d4e6663af8a2aeb +size 2889513984 diff --git a/Mio-Qwen3-4B.i1-Q5_K_S.gguf b/Mio-Qwen3-4B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e9bc81a --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f82a70b96fe34a9daf4a7141ebf5d4055fe5eac38920763404c5311df27e59c +size 2823711744 diff --git a/Mio-Qwen3-4B.i1-Q6_K.gguf b/Mio-Qwen3-4B.i1-Q6_K.gguf new file mode 100644 index 0000000..6036e92 --- /dev/null +++ b/Mio-Qwen3-4B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586fb6ee73d9c2d714f37dffe091d72d7ec36cfc0f49877be353f3e08cffd541 +size 3306261504 diff --git a/Mio-Qwen3-4B.imatrix.gguf b/Mio-Qwen3-4B.imatrix.gguf new file mode 100644 index 0000000..62d362d --- /dev/null +++ b/Mio-Qwen3-4B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f3946c596dbf0feabb53147813d51b3fbb11c8d1d0c151796d627797d4b5e89 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c04cfe3 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: RiiShin/Mio-Qwen3-4B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/RiiShin/Mio-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mio-Qwen3-4B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Mio-Qwen3-4B-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/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mio-Qwen3-4B-i1-GGUF/resolve/main/Mio-Qwen3-4B.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. + +