commit 46241ac0481ba9ff53a0978d74410c180770f601 Author: ModelHub XC Date: Wed Jun 17 17:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9c1d20e --- /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 +Llama-3-8B-Stroganoff-4.0.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Stroganoff-4.0.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ1_M.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ1_M.gguf new file mode 100644 index 0000000..5391ec9 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d4a8dba724eefe4317786a9c0859fb302a1adb03b7de4c3b24ef2b4bae590af +size 2161982656 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ1_S.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ1_S.gguf new file mode 100644 index 0000000..4f6b919 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ea3a6f147b5cdd6077c49649aa02be147bed9b89161f350b521a94e2a83705 +size 2019638464 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ2_M.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ2_M.gguf new file mode 100644 index 0000000..62492e7 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:007f6e5b3b7818a8e43b02af46866b0f85eeff589298669cd42d2faaf4b5eba1 +size 2948292608 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ2_S.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ2_S.gguf new file mode 100644 index 0000000..76cba6f --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a985559b7dbcd09e0731192a15e2b7e1cd52ef76a125795a453fe1b8eb5a5c +size 2758500352 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ2_XS.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e49a669 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c3b38c3ecce1e7b28b7b6ba1862921da58dbcb5a6f3c7c99537fe817327229d +size 2605792448 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ2_XXS.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ee00f0b --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1ee3922b5db02814c1e5bc6c275bfafa09b1b66c3db9253c8e951748a4ecd1 +size 2399222976 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ3_M.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ3_M.gguf new file mode 100644 index 0000000..ae8cfd1 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700c6cbdcc68116d4294d3ce50d209813f4f20449bf2fa33a1f211324b026d26 +size 3784836160 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ3_S.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ3_S.gguf new file mode 100644 index 0000000..85dfff7 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492f36c3d5dbeca029bd55bbd7c6d5ef8802b170f14b4158a5796ff31bef2bfb +size 3682337856 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ3_XS.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ3_XS.gguf new file mode 100644 index 0000000..3f51044 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d0d2a033e0c855fb4021fe3cfebc69be252020a43c60a325ecff5f2bed5788c +size 3518760000 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ3_XXS.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..57e3d35 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee9fea1d29e7c24f3c0f9b2b3c39a0fc06142a2033d175ab5e9a838c3d7e272 +size 3274924032 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-IQ4_XS.gguf b/Llama-3-8B-Stroganoff-4.0.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e718bf5 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e81dfc4d9469c6a879404d07b47098644f30313d652cb3d8ba7a3726b9c32d0 +size 4447676288 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q2_K.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q2_K.gguf new file mode 100644 index 0000000..df26f06 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f068b1f19c7d3908e5d9286bb5a28a68e9994f2e3b6abdbe716bb0e022d6cf8 +size 3179143424 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_L.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_L.gguf new file mode 100644 index 0000000..61cfb13 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb384a9f8a61f59704d3689f5c6f60683b018115eb0a7d3945fdef66c98eab29 +size 4321969216 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_M.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8f5bcd4 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae16b873c0b5f3a8d8a7d0387e0e4b88b619c9381343d283abececaaa63bfd42 +size 4018930752 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_S.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_S.gguf new file mode 100644 index 0000000..57083e9 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6987ab09c538877b12f74a991da74aa23f338f21490a0d51e87d6c223d043398 +size 3664512064 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q4_0.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q4_0.gguf new file mode 100644 index 0000000..c3911f9 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08f5504c0ac8d556e111e54bb4ae722e141c88946ed95c7441acdb1746b614f3 +size 4675905664 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_4.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..7a6ad2a --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb67f9298e3ed991149adcd64220c67f5abb8cc4ba5d8e63c29f73ae6a4f870 +size 4661225600 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_8.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..f8e5bd5 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:886b95518d242ed10bd33bf6e070a62c8985ebfd0c71167359203bfa33443303 +size 4661225600 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_8_8.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..6aac8b2 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a76a82501dfc511c860fdd41df588bb71ee4b706f6c0aaad3613a4619733db6 +size 4661225600 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q4_K_M.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q4_K_M.gguf new file mode 100644 index 0000000..745eab7 --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5f2e261bd4d041d8a6b971ea2da9d6c0060d70aa6c35877666093164147e08 +size 4920748160 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q4_K_S.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8df933b --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b642d3fb883e7474be1195662193e00a52abc90a9e0da6b887d4d554541e3025 +size 4692682880 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q5_K_M.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q5_K_M.gguf new file mode 100644 index 0000000..286966e --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d5aa6cf7c950da97e163609d50339e39b901e7648e9e4c799172c06ff109ae6 +size 5733002368 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q5_K_S.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b2ff4dc --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e233382bc4d222f8b68d4629bca341bc86a76fb704d5114d8e53d6d1a04e11 +size 5599308928 diff --git a/Llama-3-8B-Stroganoff-4.0.i1-Q6_K.gguf b/Llama-3-8B-Stroganoff-4.0.i1-Q6_K.gguf new file mode 100644 index 0000000..dd059bf --- /dev/null +++ b/Llama-3-8B-Stroganoff-4.0.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151a76184c32bb23530d88faebf4dea0e7d3928926277384a563ca78ddd4b2b3 +size 6596022464 diff --git a/README.md b/README.md new file mode 100644 index 0000000..976814f --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: HiroseKoichi/Llama-3-8B-Stroganoff-4.0 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- nsfw +- not-for-all-audiences +- llama-3 +- text-generation-inference +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/HiroseKoichi/Llama-3-8B-Stroganoff-4.0 + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-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/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Stroganoff-4.0-i1-GGUF/resolve/main/Llama-3-8B-Stroganoff-4.0.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..ed5efce --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d729e94c4fd991a1797781cd40c65081400387d83c13356f65d29adab15493b +size 4988157