commit 9e1182bd133afe2c66f5993b677422cebd9c82c5 Author: ModelHub XC Date: Mon Apr 13 23:15:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f8ac983 --- /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-Coder-0.5B-QwQ-draft.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_M.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_M.gguf new file mode 100644 index 0000000..4a0bd05 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8a46505eb57718fde83e0f991f25ca31a01c409d0be160c473050a0ae4fd73 +size 318099776 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_S.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_S.gguf new file mode 100644 index 0000000..63e05f3 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91535992540d0d162ccf6be518d18005a14d7551a9329cb490d04ae2550d8dd1 +size 315954752 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_M.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_M.gguf new file mode 100644 index 0000000..d9ec0c8 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451a3be77cbe9c6ef9de820e41c96931dbf1c4f4b8021cff722094f266b24629 +size 328722752 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_S.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_S.gguf new file mode 100644 index 0000000..f4f0b0c --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3604c74d8c66a648e3fb2af28ec6db6dd0372b595494937d39366942bd7e1c95 +size 325862720 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XS.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5126375 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176736a6e8bd95ab437845dc43065362096a504a59e004c7a04f1f45b344570b +size 324534848 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XXS.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..10de591 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b247e899da4998e3b7c7b131f60b5635ec4b27d9e4f5cb003d444b413446dd28 +size 321674816 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_M.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_M.gguf new file mode 100644 index 0000000..4303c33 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50d9bec56485f53a4ea161be0b3238b22cfbd7384cee57d06f510d001c99fd94 +size 342877760 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_S.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_S.gguf new file mode 100644 index 0000000..6c61f92 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46899f1fa430b34c4fe4621c9d4b8afbdf90828797fd67200056cd37ec78e965 +size 338732864 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XS.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XS.gguf new file mode 100644 index 0000000..5e238f8 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414b591a3bccd4db47753d433bd4639f73d1b75a43616910134a9f86d3cb65de +size 338732864 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XXS.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a6d9e21 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202eeb12285836664c86ab08202ccdbc6608351bad01734fb9831129615cf125 +size 333829952 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_NL.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_NL.gguf new file mode 100644 index 0000000..602a242 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e7b62479aaa21d37975e44123fa85e48d7de4acf54a3e290988d7d86761766 +size 352796480 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_XS.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ef1285d --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0e5e1f6085041295b508948623ed8a4119db4026fc415543325b9005d5b3ac +size 349527872 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K.gguf new file mode 100644 index 0000000..27c63fb --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20cadd0d915b24a19a38b5b9c0c2d261d3ed1834a41cdc75df34f317278d82d0 +size 338732864 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K_S.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ffde9a5 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0789e899ed94a15e51aa80261be080d4c6bbce03f0c5dabb10d7bf665ba1c89 +size 331174208 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_L.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_L.gguf new file mode 100644 index 0000000..5122429 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac642622d1c36b0d06a5b727b51fdb12e50f69ba6f3ce300a2fe43515f080b83 +size 369483584 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_M.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_M.gguf new file mode 100644 index 0000000..00c360f --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3764c1bd3f67f9bf7c21e71731d8380cab608aff31093d600efde5fae843f03 +size 355592000 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_S.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b242ef1 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364cad66a247139d029ff731b98676a06a79b9ed1a0cb4fac1229019b4105298 +size 338388800 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_0.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_0.gguf new file mode 100644 index 0000000..86f45bc --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33e592b01931deb7c1eae7f811337a6f55cc74db7f451cd8b21798a5e41cfc1 +size 353097536 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_1.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_1.gguf new file mode 100644 index 0000000..dbf8811 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79aeec955f9ca326de07c126168f089c848b979ede08703e1b24db27d0eeeb4e +size 374644544 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_M.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a5775c5 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60f04557cbfd69671e7993715e17ca664dd0d2028e7c199d67d6ded8608c379 +size 397933376 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_S.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_S.gguf new file mode 100644 index 0000000..43e8fbe --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:246fb3e3567521813203934f5c28ac376167274bafe8426070725d1b58400e25 +size 385597248 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_M.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_M.gguf new file mode 100644 index 0000000..cb0d56f --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8485f1d81ffc0474c829f79b7bcae6bcdb64119d5509fed40d4e927bf4503e60 +size 420211520 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_S.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_S.gguf new file mode 100644 index 0000000..250d43a --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:303cdf13c53377ac1cf7a2f8cdc7f931f7d8a7f2775a4197ba92b8276a84f9f3 +size 412835648 diff --git a/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q6_K.gguf b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q6_K.gguf new file mode 100644 index 0000000..77c8057 --- /dev/null +++ b/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ef50bd40990da22fe9e8eafa01302f4870b5ef96414a466c0ca74e1c029fde +size 505861952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e7706c6 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft +datasets: +- PowerInfer/QWQ-LONGCOT-500K +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-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-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-0.5B-QwQ-draft-i1-GGUF/resolve/main/Qwen2.5-Coder-0.5B-QwQ-draft.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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..06238af --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af73107eae26fa02a97f2767f126c1f49773069805b581f776ce81f0dafc595e +size 988597