commit 80a317c8ca6a16acc87d5d2006481f74b6ab28de Author: ModelHub XC Date: Wed Apr 22 12:06:38 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marco-Nano-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4f251a8 --- /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 +Marco-Nano-Instruct.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-Nano-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marco-Nano-Instruct.i1-IQ1_M.gguf b/Marco-Nano-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..b82604b --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67fa9cd1ca96f9dd138fc90fdc0aad34b26382539a96b3cc584bf5dddf5bcf14 +size 2745041696 diff --git a/Marco-Nano-Instruct.i1-IQ1_S.gguf b/Marco-Nano-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..50c8e5c --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1079a00d81e1ac699f91bce95ad16b97e003cd4d8855eee0a045997c9bc3686 +size 2623243040 diff --git a/Marco-Nano-Instruct.i1-IQ2_M.gguf b/Marco-Nano-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..f61825f --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6daaf53c21d5d89fff9a6b954fcbbeae1ce28a02c8344c5a19e97cf24e683bef +size 3282928416 diff --git a/Marco-Nano-Instruct.i1-IQ2_S.gguf b/Marco-Nano-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..eed2f90 --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03802d9b9205bd5d29b50b43b0460f5b8ee0adc6e97d453ee15f6c4ddd2364f +size 3120530208 diff --git a/Marco-Nano-Instruct.i1-IQ2_XS.gguf b/Marco-Nano-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5b1063d --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867aa743394b908006a258dc7232c3b92dc96ebbef4ff071b836d4e54806be00 +size 3112272672 diff --git a/Marco-Nano-Instruct.i1-IQ2_XXS.gguf b/Marco-Nano-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..25563a6 --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6156ef89fc93b935cdb7f8f672057d20f58ae2cfccb2d36114ed2d1ddde13bef +size 2948039456 diff --git a/Marco-Nano-Instruct.i1-IQ3_M.gguf b/Marco-Nano-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..4f9644d --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df2e592cacb68b0490063dafb2cc6aa4c499cb4835b1f54861d7c5ccbdecbdc +size 3913994016 diff --git a/Marco-Nano-Instruct.i1-IQ3_S.gguf b/Marco-Nano-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..74858aa --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c52a69f1148f6dba8b78aeee4e10b128e609a8062ade5f850b1a1b9f3099d071 +size 3868086048 diff --git a/Marco-Nano-Instruct.i1-IQ3_XS.gguf b/Marco-Nano-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..9056dae --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce3eec2f78ab44851401b3e011225365cc8c36cb54e400b52ebd6595bb9ef42 +size 3684355872 diff --git a/Marco-Nano-Instruct.i1-IQ3_XXS.gguf b/Marco-Nano-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e077a26 --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aba96eaf2007aa8ae7bfe1f994135a4699d9d9f7ccd5eca00f5301cca8af7a2 +size 3596944160 diff --git a/Marco-Nano-Instruct.i1-IQ4_NL.gguf b/Marco-Nano-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..ca85b88 --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8100eaba83a4259af91105c30d09021d0132dd7c4b80bbca66ebf70cb712cd +size 4569976608 diff --git a/Marco-Nano-Instruct.i1-IQ4_XS.gguf b/Marco-Nano-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..671dbef --- /dev/null +++ b/Marco-Nano-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e857bd1d480f5a64b40cd02d4d106483948c15ff4fa102b3687421298eaf1786 +size 4404825888 diff --git a/Marco-Nano-Instruct.i1-Q2_K.gguf b/Marco-Nano-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..96b9a27 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38404eee007e5e5987edfb30e2685f933775fa537c42f794a5f8f2512090cbe +size 3340291872 diff --git a/Marco-Nano-Instruct.i1-Q2_K_S.gguf b/Marco-Nano-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..43d358b --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6161194c7ac75f89f2ea8fb0fed10274acbdff2644ecff17eaff27cbb782484b +size 3365556000 diff --git a/Marco-Nano-Instruct.i1-Q3_K_L.gguf b/Marco-Nano-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..33e0151 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88c469e9fdad4bf775e9f24762a96d172d7a0d31208e32053773b4be0339777 +size 4369731360 diff --git a/Marco-Nano-Instruct.i1-Q3_K_M.gguf b/Marco-Nano-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b44b379 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6d3a6ce335e0cbed6e0bd3f4256642cf0ea28545eee26f03689e054f69c59b +size 4205039392 diff --git a/Marco-Nano-Instruct.i1-Q3_K_S.gguf b/Marco-Nano-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7e42e3d --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41e2581432619a0a9d4f65cae4e425e6f3b1a160d59442aba354d503e286bee2 +size 3868086048 diff --git a/Marco-Nano-Instruct.i1-Q4_0.gguf b/Marco-Nano-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..3f027f0 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b033df313fa23ea924eeba2366390b667565db73bc74b4c1f65ae337327107 +size 4587081504 diff --git a/Marco-Nano-Instruct.i1-Q4_1.gguf b/Marco-Nano-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..65ebdc0 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a498034404e987392254f1b0fca7fa993495ed2eeb05e8b86cfaaa6ca382e82e +size 5059923744 diff --git a/Marco-Nano-Instruct.i1-Q4_K_M.gguf b/Marco-Nano-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ff63f10 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef8fab7a95287b9ebdd7b710dd54b88bb4a334f4aa6f662e579fd15795311d7c +size 5371989792 diff --git a/Marco-Nano-Instruct.i1-Q4_K_S.gguf b/Marco-Nano-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..754abd7 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76025f4d51dea8523bdc62c86f6af11d55a88efcc3b968c317d7be8e16b85540 +size 4906897184 diff --git a/Marco-Nano-Instruct.i1-Q5_K_M.gguf b/Marco-Nano-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b720b86 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac90932a4cba09deccd0d312a7119c83576dfcfb0f114aec0e31c6ac55355027 +size 6110580512 diff --git a/Marco-Nano-Instruct.i1-Q5_K_S.gguf b/Marco-Nano-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5c02ce9 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c6f0cab1e857c8f53b7eddb99e19bf39b8e22c19e3bddbbe5395ac8254cbfe +size 5709516576 diff --git a/Marco-Nano-Instruct.i1-Q6_K.gguf b/Marco-Nano-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..f49a808 --- /dev/null +++ b/Marco-Nano-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f65fe78da93ae339ce306f309983c82b55e9ef8fbc1d59516b5c08bedb7826c +size 7209635616 diff --git a/Marco-Nano-Instruct.imatrix.gguf b/Marco-Nano-Instruct.imatrix.gguf new file mode 100644 index 0000000..0152d86 --- /dev/null +++ b/Marco-Nano-Instruct.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31aa386a7d8b1901efc96161c7d3655e96d0ae9a29f04ff451d61b063246199e +size 63993376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..385411f --- /dev/null +++ b/README.md @@ -0,0 +1,129 @@ +--- +base_model: AIDC-AI/Marco-Nano-Instruct +datasets: +- allenai/Dolci-Instruct-SFT +- nvidia/Nemotron-Cascade-2-SFT-Data +- nvidia/Nemotron-RL-instruction_following +- nvidia/Nemotron-RL-instruction_following-structured_outputs +- nvidia/Nemotron-RL-ReasoningGym-v1 +- nvidia/Nemotron-RL-knowledge-mcqa +- nvidia/Nemotron-Cascade-RL-RLHF +- BytedTsinghua-SIA/DAPO-Math-17k +- Skywork/Skywork-OR1-RL-Data +- nvidia/Nemotron-SFT-Multilingual-v1 +language: +- en +- zh +- ar +- de +- es +- fr +- ko +- ja +- pt +- tr +- id +- it +- nl +- pl +- ru +- vi +- th +- he +- uk +- ms +- bn +- cs +- ur +- kk +- el +- ro +- hu +- ne +- az +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- moe +- mixture-of-experts +- multilingual +- upcycling +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/AIDC-AI/Marco-Nano-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Marco-Nano-Instruct-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Marco-Nano-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/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.8 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 4.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-Nano-Instruct-i1-GGUF/resolve/main/Marco-Nano-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 7.3 | 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. + +