commit 1a90b8d1857d969fef7a46b5aee708ab1199d115 Author: ModelHub XC Date: Fri Jun 19 16:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f2614e1 --- /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 +FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..a358979 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f14330a32e0004211694fc38e82b7ac05f6a0ccbcfc98fb6f5e6cc5f6a55292 +size 924188320 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..d0aae71 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2430fc1bd2887f95cf6afdbbbb51105b61b70c3f343feed8206bd0b7fd24b917 +size 868155040 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..304b60e --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ae8d24326e23512db00c8b38ec4aaee56aee5544075e33fb9f1154777c6fd1 +size 1229029024 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..48859f1 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6abe6c1caaf573db30dcf1938dcb0ca33d552b93a866e0cc611b05b3d21be96 +size 1154317984 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d5239f7 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bc0427bd4bf9d589226d67d5740398415e6a01451b0b634338ccb7e645b3658 +size 1100545696 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..289c9fc --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:460a192e4709f073cca2f5f181eec5512b0b0f83b76362e3a9b344f0e27e8c21 +size 1017577120 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..fd8d41e --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f5fa391126a516872ab5d3437fd4965bb7b22f6d3a43587f93176f3e385dcb +size 1599665824 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..4fe6208 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8fe4b4aeb39cd38a4b071b9609699d3016fae189b3052ada9601e3405e70e87 +size 1542846112 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c348588 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a20c758a04f020a0918454180f2061ae79742c4081c3182828ba07c4833d839d +size 1476785824 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5cb3eef --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51657d48aa7053f01c92e5e5534c55a1a63b3563f7c8e698a7603a97584386e7 +size 1348763296 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..90198d4 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3467ad3277f7d4a06232cf84672634be108adfd354127aae035a0689d3a9b50b +size 1917187744 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0a48aa9 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6938281046d6ab33c9a825b96360f44faf8e0ff3d488a7f6102d782bcf9bb9 +size 1829107360 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..4dbf8fe --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e70f81a351ea52a6a8c03d2a1318a684cd5cf25119d0b913cceb8e2a99fbb1 +size 1363932832 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..3d57d0c --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ac2637c260fc4bfd8725b70ffcb115dad2d6f63cf2e268cb9b5d12efc8244e +size 1274279584 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..76a772c --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8e8910e1f3d843c6ff65e2b06ad67c77c3813e7629e1776decf7b91948e97d +size 1815344800 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e80519c --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd2e688ec70d9b5d82c720482f055b7ccfd44298d1b540c2fa8afadf7869bbf7 +size 1687156384 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..f07eece --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c45001bc2e4db2e4bb76c464b96ca3d039acff6e21ffc5cf2015f59a3a84d4 +size 1542846112 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..47b8674 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71885ed8ab28fb4d9d155c4cccf2ea32096bd2ecab031e43c37dc1fcf08f024 +size 1921906336 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..d0f0364 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb1fe478d7431f301a03da2bf7a5277cf17c64462016b0d337ff9fbdbb773a8f +size 2093348512 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ca9cbd3 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960813bd1b20146aff2cf38988d977f750b86ab5cd8ee78c4ae7a854cac6fbb4 +size 2019374752 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..3c28717 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9923ff616cefac2b2441805db8487b31f0124000764f6d174c2a597dfcb8854 +size 1928197792 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7181064 --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87a4ba696c08eeb395cbe367039c17fa4e49704a8a137950c57284726116106 +size 2322151072 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3c9b7ac --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33c0f2d1d69554781495a5e8d95cb126c62221f82e3025cde7f5bc8ab0ac685 +size 2269509280 diff --git a/FuseChat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf b/FuseChat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..02f58bb --- /dev/null +++ b/FuseChat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b46c4ad5c43f6f56278aabc0fe2fd12411dfba49fee32990921dd1c1778b63e +size 2643850912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4f869c4 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: FuseAI/FuseChat-Llama-3.2-3B-Instruct +datasets: +- FuseAI/FuseChat-3.0-DPO-Data +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/FuseAI/FuseChat-Llama-3.2-3B-Instruct + + +static quants are available at https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-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/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-3B-Instruct-i1-GGUF/resolve/main/FuseChat-Llama-3.2-3B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | 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..5e10be4 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32330575cfa85b7c3e9fcb4afd7e53915a6788e1e2f265cdf4be164dd01da099 +size 2988377