commit 3ca9a18476e482499ffc658d47ef213a0de5b553 Author: ModelHub XC Date: Thu Oct 1 21:41:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..69d9943 --- /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 +Qwen3-4B-tamil-16bit-Instruct.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tamil-16bit-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_M.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..55b0d07 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41b3b6b57a3fc13018254c9873507f181981aef5c080d0b2f597cd436b60988 +size 1127019008 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_S.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..69e0d93 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e4fbce016a072215867d3c365b226715df4ca1d60105fd290af17dc48dead7b +size 1055257088 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_M.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..9367169 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acce48aabe90fd84dc668d181ac8fe46610b2c063123a202d6b8e1bc5ace94d6 +size 1512985088 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_S.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..cca38ce --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c19744c086f4403c960e96c34a4c2d7c0c91a315248d166d6d252a2c7893c5 +size 1417302528 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XS.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4b5d214 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c847478059137bd62de3f9f33c31bf741a9718f2c40f666db9b86e9f7996ba +size 1354101248 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XXS.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a138c8f --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c1c3e256d5ce49df4b7875c48f5293f52b9a9e05f2b51f9b9b5a9d74eeef150 +size 1246622208 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_M.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..aaa90ec --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1441ef9e037de6169b08fa22c2182c7e66a511adbb5306a252950f06a54327c7 +size 1962897408 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_S.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..9ccad6b --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc0694a4a200beb58ae452081ace643e1ac24e2a6366f5374b941ff6a17d61ae +size 1899532288 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XS.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..fbb341d --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06ba9c3c420d5e895a2660f53e6d1749322d9b89318c079bfa43299911c08c8 +size 1814376448 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XXS.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a45d759 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c39f4988594e2f969278601f72970726c75cf9fa3ce9d0eb9a5c98c8d3528c53 +size 1670189568 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_NL.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..fd445a0 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c79f78b4b0235d22cfe86612c49e5d6f9b547ef14175a3568f88cd6c60ce16d8 +size 2381344768 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_XS.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..78cfcc9 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142bb1ba72fb4c46b5b991cb1939ba19a1e67998379ed6c9e3419a3a0566ab3f +size 2270752768 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..03bb28c --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d83df4fd3ef927a1df74f9857b7a650f233b73b042dc14b800ddbb0861419c +size 1669500928 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K_S.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..0754649 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e84f6f47ca9b3e102b1040d3652a694f296759eac82a1ba2cf082eaf217d1e +size 1563455488 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_L.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2fc32e0 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9e5ac5d1f002cb75d159027732baa865276375bfbf54364a128f58dcf4c2de +size 2239787008 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_M.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2f92c20 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c5f8c34bdcad2a2d82d278a88da3d484fe8f959fbef5b5632bdfd88d931fcd +size 2075619328 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_S.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9211c06 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc0713f54f5e25b7bd730f42931e13801ddb3ba76f7e44f9c7615f642fc8aaa +size 1886998528 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_0.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..3b23a35 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f87bb00d2e030a07fe823d893bf7811714a6584057f60b71fcdffd18113c1f +size 2375774208 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_1.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..879e7c1 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f832a3460b3ef8de282a454987350eca383bb155c327df3107d406c1993ec29 +size 2596630528 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_M.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..513243e --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4261dd33f5bae37942132d8fc9bb3c64e87f07efa9675527fd63c0987b0b05ba +size 2497282048 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_S.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..34b97af --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad33d0f64e8cfc998d7848d91dc947834398fd81078c6b15270f03d45b83ba88 +size 2383310848 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_M.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..26d8d40 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90374342365d9354e208276c81aab1f48ca07070b010245f7fd542df47e68b91 +size 2889515008 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_S.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e181c90 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4af8245f62a07bca337e71b2027b801a34340a63ec85bd90196d9221350f83e +size 2823712768 diff --git a/Qwen3-4B-tamil-16bit-Instruct.i1-Q6_K.gguf b/Qwen3-4B-tamil-16bit-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..b5d446c --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154aa77c1e0fed7dae8d550dec27ea625e8a18aece0a3130285159c48faf6d51 +size 3306262528 diff --git a/Qwen3-4B-tamil-16bit-Instruct.imatrix.gguf b/Qwen3-4B-tamil-16bit-Instruct.imatrix.gguf new file mode 100644 index 0000000..302e414 --- /dev/null +++ b/Qwen3-4B-tamil-16bit-Instruct.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0208460bc214fbe6eeb7ca02c5bd5c12bbfdd3f319117cf65a8103c318b2c8 +size 3872640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..633243e --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: sabaridsnfuji/Qwen3-4B-tamil-16bit-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/sabaridsnfuji/Qwen3-4B-tamil-16bit-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-tamil-16bit-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-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-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 2.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 2.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tamil-16bit-Instruct-i1-GGUF/resolve/main/Qwen3-4B-tamil-16bit-Instruct.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. + +