commit 65c4fb318a653d3b465886664edcf739139f80d9 Author: ModelHub XC Date: Mon Apr 13 09:06:02 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..db40ba5 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.2-Instruct-Thinking-v0.1-1B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_M.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_M.gguf new file mode 100644 index 0000000..06bce7d --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1856d562751f47351a7532e78076c67f9153d082480cc24405f519ca273f1f07 +size 413610336 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_S.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_S.gguf new file mode 100644 index 0000000..412edc6 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a73375085c52f223afb844f7f7b44191a3a90ceea47024f7a9d98116eb678e +size 393556320 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_M.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_M.gguf new file mode 100644 index 0000000..fb4792e --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5354f8f21abcfb443c5ad72a2664ef1882e1c2b88d849a7486bc07720f2eb6 +size 515453280 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_S.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_S.gguf new file mode 100644 index 0000000..7cdaaeb --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd2b60c2b3ab3f9aad30f27a92c0d5287c9d4af494ecf605eacdaa4da058b828 +size 488714592 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XS.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..953cfdb --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e8d20474ac5f9c8e73dd3823a2cab3590e8c35498c1cc1f2560d5d18afaedb +size 475869536 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XXS.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..89111d5 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f952d3d51688d72c95b3a47a5491ff9263182716c11fdabb5aae0f3231ff2d3d +size 447033696 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_M.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_M.gguf new file mode 100644 index 0000000..2149a51 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:185ec2745a60007d00a96956738932e36f45f1207a6d64fdf120878afbd91352 +size 657293664 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_S.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_S.gguf new file mode 100644 index 0000000..6fe438b --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d58607e39f423995ddc1bf4e8f85e6e20fb32bd6222ba665540c2ea20c0baa +size 643924320 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XS.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ffd7a0c --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6631543f7870c59a26ae31817dd9405a0c42604c68f645088096910acb42f5bb +size 621117792 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XXS.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1a631c9 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:160342d652cedc5532671c721d827b4da1952d236686d5d4f3722b808a3abac8 +size 562114912 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_NL.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..faf2abc --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23fbef16b577d4b14007664350bbc89b595d817bbe8953a305a572dfee679f59 +size 773030240 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_XS.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..bf6fc52 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41c2c6713b38f146ef1436c53d1a56dab30709ad8cff38bbe00c8dcc271c3a33 +size 743145824 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K.gguf new file mode 100644 index 0000000..dbe7ec9 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e650eaa67443855a38fe1f05648532e6c64d06544d2e28b2039cc80623826626 +size 580878688 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K_S.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..91fbec3 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8475483859f6b8bb3befd9a69340968993e0d148d00a2ad8e718fb161dfc47 +size 554664288 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_L.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..b92d11b --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c786cf36651e93c41b28ec88fee259ba944eae88617fe8451181e13ffa3602c5 +size 732528992 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_M.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4d3d9fc --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c80ae424704e13ba010dc606daee393e4e5c3c7b314cf4c40911c388de5074d +size 690848096 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_S.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ad3973f --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff0e0ee6b13f084af3d2877642bf9a5eb34035acbece7371e83e13c355b6b31 +size 641696096 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_0.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_0.gguf new file mode 100644 index 0000000..354f988 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87820aa2c817e98dca8f0bf62a73a178df015b712849e68c0ed83e4e29eef66d +size 773030240 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_1.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_1.gguf new file mode 100644 index 0000000..c87e049 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:941137261ed662a3b6cab1f443217e3b24d63b7f2204814acab121948cdee692 +size 831750496 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_M.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..6bfd5fe --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7676d3817a31cb5e7f2d26bec7f24632e4f8af5f5944c60d28c8581a2a88c60f +size 807698784 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_S.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..a26d948 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d3d6b69a93aba0c458425ac55067b50ab676f30082e18b4d6f7be203c545e0b +size 775651680 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_M.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2f5c410 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6ca34883378e6cec081fc0899b759f9cc5178d9ce5f030e45405dd5a7e28083 +size 911507808 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_S.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8cc5ab3 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:191cbd15e68acc88a2956f13e95db0793ae8e02d07dc44a26e7b1d569b7cf052 +size 892567904 diff --git a/L3.2-Instruct-Thinking-v0.1-1B.i1-Q6_K.gguf b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q6_K.gguf new file mode 100644 index 0000000..7cbcff2 --- /dev/null +++ b/L3.2-Instruct-Thinking-v0.1-1B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19884359558a21a1cde8f6352e93eef271805f8ba2cb2754c7d1189241f0db0c +size 1021804896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e79fbc --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: PJMixers-Dev/L3.2-Instruct-Thinking-v0.1-1B +datasets: +- PJMixers-Dev/Weyaxi_HelpSteer-filtered-gemini-2.0-flash-thinking-exp-1219-CustomShareGPT +- PJMixers-Dev/lmsys-chat-1m-gemini-2.0-flash-thinking-exp-1219-CustomShareGPT +- PJMixers-Dev/allenai_WildChat-1M-gemini-2.0-flash-thinking-exp-1219-CustomShareGPT +- PJMixers-Dev/allenai_WildChat-1M-gemini-2.0-flash-exp-ShareGPT +- PJMixers-Dev/grimulkan_theory-of-mind-gemini-2.0-flash-exp-ShareGPT +- PJMixers-Dev/grimulkan_physical-reasoning-gemini-2.0-flash-exp-ShareGPT +- PJMixers-Dev/WizardLMTeam_WizardLM_evol_instruct_70k-gemini-2.0-flash-thinking-exp-1219-CustomShareGPT +- PJMixers-Dev/WizardLMTeam_WizardLM_evol_instruct_70k-gemini-2.0-flash-exp-ShareGPT +- PJMixers-Dev/allenai_WildChat-1M-gemini-exp-1206-ShareGPT +- PJMixers-Dev/grimulkan_theory-of-mind-gemini-exp-1206-ShareGPT +- PJMixers-Dev/FreedomIntelligence_medical-o1-reasoning-SFT-CustomShareGPT +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/PJMixers-Dev/L3.2-Instruct-Thinking-v0.1-1B + + +static quants are available at https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-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/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q4_1.gguf) | i1-Q4_1 | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/L3.2-Instruct-Thinking-v0.1-1B-i1-GGUF/resolve/main/L3.2-Instruct-Thinking-v0.1-1B.i1-Q6_K.gguf) | i1-Q6_K | 1.1 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..5b0166e --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58eb0d6968716ceac6ec1149e1e042472c57e6c0b050b4cdd6923e4811f60826 +size 1314413