commit 082d41895e782158c2e4c7349956665d56c734d6 Author: ModelHub XC Date: Tue Jun 30 05:45:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c07704a --- /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 +Cosmos-8B-Instruct-SFT.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Cosmos-8B-Instruct-SFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ1_M.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..4727c75 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d54f388fc9fa077b57b8fe42eff78f3ed05f28338030b8cb3a2f2bd2cb3ff4 +size 2161973024 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ1_S.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..b6e691e --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b17b53078ea7283583a7a1f3c97c43d3fed43d3421dcee9528ac80ca3489e76 +size 2019628832 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ2_M.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..9211c87 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d47f455c6f1b3fefcc08800027d055a0128924d0eb5643118a987b41cee7e9e +size 2948282144 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ2_S.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..170ab7f --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d965d798c12832f44b8f3a7c2651c7711f72740a959fe0f988fa5d8b08c450d6 +size 2758489888 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ2_XS.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..34225e3 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1b8d19d577f31aff48c9ee0485f17645db30213ad051ca1a3496457dda89b32 +size 2605782816 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ2_XXS.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..75f16c2 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca28bec86f7ac32c35999aa31bc4ae6d8a1a29da26fcab3610556ab15c80f72 +size 2399213344 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ3_M.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..636c1f8 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7fe2e654e8b56c57b6ee4e62b02ffc87d0087c81a61478bff7f19e8ab156130 +size 3784824608 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ3_S.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..e1a4fbf --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9d3594b2c84111cb40ee30eaa799389d379726a026d94b42ee2425b21d72e5 +size 3682326304 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ3_XS.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..9e47137 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daeac445acb5b43d59d7cbf3595971aab00c9c0fb2cbec55cf8300b0b6ac71cb +size 3518748448 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ3_XXS.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4f9e67a --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714ed617da654f3ea10895757daf6d8f0a37727ec9a487be2135c6d939950961 +size 3274913568 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ4_NL.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a6eb0a0 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bdaf29bd526c61636b2f27a014e669308f20190480747f6f0d22ba61e4fef0a +size 4677990176 diff --git a/Cosmos-8B-Instruct-SFT.i1-IQ4_XS.gguf b/Cosmos-8B-Instruct-SFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e40e1af --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d9a46c0a39b62ded3cf29fa2e44b50cdc87481c0f75114ba2dee6c5f5918047 +size 4447663904 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q2_K.gguf b/Cosmos-8B-Instruct-SFT.i1-Q2_K.gguf new file mode 100644 index 0000000..61de487 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bd3da37927aa6fb08996d4785fa90771dbc979fc771a059845f00d9111ac2eb +size 3179132704 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q2_K_S.gguf b/Cosmos-8B-Instruct-SFT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..b148dac --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:533f1f6c754ed7a85e6c723971b87e5bc508339a27e71eb084e4fe50e0ce7760 +size 2988816160 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q3_K_L.gguf b/Cosmos-8B-Instruct-SFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..05ceecd --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b731acba05aab77597f2431346791a0e872d5dbbb8ee6ba76c11d4be11c17d8e +size 4321957664 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q3_K_M.gguf b/Cosmos-8B-Instruct-SFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..29b4839 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:070e2b0f45bffdfb8c9885c1da4f6d7d0759f38f31f59754e634e22e1e717d07 +size 4018919200 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q3_K_S.gguf b/Cosmos-8B-Instruct-SFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..5eef006 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60dd631b10e39494efcb2d4aef0992230b7a4218b87a16c1119c4ee9b5295e9d +size 3664500512 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q4_0.gguf b/Cosmos-8B-Instruct-SFT.i1-Q4_0.gguf new file mode 100644 index 0000000..d55db77 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0213a5887739c5cfb97a3d8a28115536baec007407e05001502223877d25b66 +size 4675893024 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q4_1.gguf b/Cosmos-8B-Instruct-SFT.i1-Q4_1.gguf new file mode 100644 index 0000000..8bc6e06 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a9656519b2aec3d0278eb65cf2391d9e77fb32ce9da58e57b37054cb4faaf96 +size 5130254112 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q4_K_M.gguf b/Cosmos-8B-Instruct-SFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..7958b3c --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c249390dbc8c324680ec00a67c8fcaf44e804c33ff13d6969c9455033a981f7a +size 4920735520 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q4_K_S.gguf b/Cosmos-8B-Instruct-SFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..dbcd100 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222103a66f82087c374cc7acb878d351490a81a51ababcf9f96122ee5833c237 +size 4692670240 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q5_K_M.gguf b/Cosmos-8B-Instruct-SFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..42e015d --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d242339be8b4fdecddeacfac4ea392e120c0b716b337fee0715566aff8a6096c +size 5732988704 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q5_K_S.gguf b/Cosmos-8B-Instruct-SFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8f85943 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a49cea0f87deaa91e4bf39220c73a6983fbb7334233309d61efcdd4e5aaeeea7 +size 5599295264 diff --git a/Cosmos-8B-Instruct-SFT.i1-Q6_K.gguf b/Cosmos-8B-Instruct-SFT.i1-Q6_K.gguf new file mode 100644 index 0000000..e55e8f3 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0fd9c1081bacdd3287016d5c8d306ef229823d95cad3a98fcab27c1f700bb3c +size 6596007712 diff --git a/Cosmos-8B-Instruct-SFT.imatrix.gguf b/Cosmos-8B-Instruct-SFT.imatrix.gguf new file mode 100644 index 0000000..f472425 --- /dev/null +++ b/Cosmos-8B-Instruct-SFT.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb9480d6f33a0acc855abf8195ecb481475b07c121614eb732869b5f9c476a8 +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ab94588 --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: ieayvaz/Cosmos-8B-Instruct-SFT +language: +- tr +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Turkish +- turkish +- Llama +- Llama3 +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/ieayvaz/Cosmos-8B-Instruct-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Cosmos-8B-Instruct-SFT-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-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/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cosmos-8B-Instruct-SFT-i1-GGUF/resolve/main/Cosmos-8B-Instruct-SFT.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. + +