commit a8f33c7ad283b53022b93f3bcec56be7bf51aa80 Author: ModelHub XC Date: Sat Oct 3 23:29:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f54bf22 --- /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 +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..cff74ba --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0832defcf7a4b780ced0704301e7430fe11f25d11838adc6898146e4fb791d2 +size 850027936 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..b695555 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744d74c6e23f313ae832968f97ef55aafb659ed2cfad9bfc6b4b21eb0122fa9d +size 791094688 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..eb504cb --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e81470d0be193df6040555860e2b727baaebad89ebdf023e4f8fcbae719d02 +size 1140516256 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..94f347e --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f29746a57bcbf3c9686cee1024ea06d4e2dfcbc436a38d5075e9978c51a5e599 +size 1061938592 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XS.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..7735507 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8670377cb56261e54fee86d21624dd9e817c5177817489a539445940669ee65 +size 1031546272 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XXS.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..fadb11e --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d1b2a419e195a939cdba50bff321f654cc74df13e6233b3e5280cb25757f02 +size 948250016 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..eafc4a0 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2336a3dadc1e43969ea1e01c5863339fef25529844eaca81685599a12f98175 +size 1488895392 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..5250180 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6a391b18c43ddc82880ee8c7be7ec3a39ca8a9f6c1dd12ee67eb3a77839e2e +size 1456864672 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XS.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e59daf7 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f89baa438e96bbde71589197351a2773e8f5a574d95778344b8e1d96e5736e +size 1391836576 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XXS.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d2bbb2f --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7287a57c069a3893a0e1432ab8152387924b03accd60743de50bf51f2bed39 +size 1282827680 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ4_XS.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b29d0a4 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a57a2c93103932bb5d6e31940d2233e1b2f7cf827171bafdc0fbc1ba707c781a +size 1739095456 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q2_K.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q2_K.gguf new file mode 100644 index 0000000..8df1583 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac9941729a93e5d01b62037f62768f3532f4fef112623b77436b4fc39cca1e3 +size 1274756512 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_L.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d70cae2 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30de99efec84d91f39cea689e306fc4df25dee047822c36434cae74e6a60942f +size 1707392416 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8806c67 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e6ff1fcce3afbeb08a67eed017982ccc5eb9155ef0596be754cbd4f4d9928da +size 1590476192 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2e34e65 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c625f8167f044e2117df5bab0e0f16256d2c81ac1896f21acc3c628cd40238 +size 1454357920 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0.gguf new file mode 100644 index 0000000..7023096 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f13c13551e8ef46e4a654afead8c275559c007d2d8d318ae1b5fa6d7f07ef35 +size 1828486560 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_4.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..217b8d1 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8687dca98a0cc4d85e2757dfdcee32b4c34eec4d52e3377f105880a0f8ab291 +size 1822850464 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_8.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..da7b893 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df0a436e37d69b26e5874a180d26d35eb8c533606d5849b245c4a7a90a725d5d +size 1822850464 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_8_8.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..68a5300 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee7e8dfdda45993a0cc15bed4173db5477df2244c677a6246a6eda88487ae1d +size 1822850464 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..588bb0f --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1d719d622f5be365e5323add8a3f72f5a5f5f3262da4e150c4b6c1c4e808cc +size 1929903520 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..07894ac --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72354fcef68dcc3c764da88abdd3ae7c2587141f9a99a291b986af05fac12226 +size 1834384800 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..53f027b --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0dc5e4dcae63a495a2f04beeeb1985d3d54b0f1cc5183353870f840a1910744 +size 2224815520 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..07f9b37 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733e334cd7bab95fb20ad6a5f642747db5417d57620ac7a01cd8f744c57a0556 +size 2169666976 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q6_K.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q6_K.gguf new file mode 100644 index 0000000..56efea9 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85544b0ef087f1cf845145342d1f086706fb1bf8bfeccaf71f7c5b4c08b33e9 +size 2538159520 diff --git a/README.md b/README.md new file mode 100644 index 0000000..131d536 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: jaeyong2/Qwen2.5-3B-Instruct-Hi-SFT +language: +- hi +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/jaeyong2/Qwen2.5-3B-Instruct-Hi-SFT + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-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/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 0.9 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q2_K.gguf) | i1-Q2_K | 1.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 1.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 1.9 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 1.9 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 1.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-i1-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | 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..5b0531f --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d18b4499f3d0dc20e6231f1744597b763736e687ee09c44bb1a71072ede471 +size 3362977