commit e57634bb6afed603f8fce805cb6602eb1f4a33b5 Author: ModelHub XC Date: Tue Apr 21 18:25:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FastThink-0.5B-Tiny-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..35e37b7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +FastThink-0.5B-Tiny.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FastThink-0.5B-Tiny.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FastThink-0.5B-Tiny.i1-IQ1_M.gguf b/FastThink-0.5B-Tiny.i1-IQ1_M.gguf new file mode 100644 index 0000000..e58e8b6 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:420382df854c486dbbf9e7d8dfbe5e691d1c958af237d2b988bd54e2e42c0f05 +size 317974976 diff --git a/FastThink-0.5B-Tiny.i1-IQ1_S.gguf b/FastThink-0.5B-Tiny.i1-IQ1_S.gguf new file mode 100644 index 0000000..c4c6864 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dde7393ceeaae479425532150e93ae448c3cd6397737d4ec67f16419762e983 +size 315829952 diff --git a/FastThink-0.5B-Tiny.i1-IQ2_M.gguf b/FastThink-0.5B-Tiny.i1-IQ2_M.gguf new file mode 100644 index 0000000..dcc5e6e --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aacaf6754f40ac22ecb8c44ff0b478a87c59d240501c3882c7cf5c4e5178f53 +size 328597952 diff --git a/FastThink-0.5B-Tiny.i1-IQ2_S.gguf b/FastThink-0.5B-Tiny.i1-IQ2_S.gguf new file mode 100644 index 0000000..6d20edc --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714d7c2802e96fcf936b4afd23ab34e82334b797a42252fc034661dd6556db3e +size 325737920 diff --git a/FastThink-0.5B-Tiny.i1-IQ2_XS.gguf b/FastThink-0.5B-Tiny.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3fad5da --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aeae1e98708a7836377ad4cedd41386d26741c9b2d5975e91b173b30fe06992 +size 324410048 diff --git a/FastThink-0.5B-Tiny.i1-IQ2_XXS.gguf b/FastThink-0.5B-Tiny.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d74b800 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1259b1c5fd3cb8a939b408ddcce020068ea6b021f47dbf3fa72977d564c0647c +size 321550016 diff --git a/FastThink-0.5B-Tiny.i1-IQ3_M.gguf b/FastThink-0.5B-Tiny.i1-IQ3_M.gguf new file mode 100644 index 0000000..f1a1787 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e4fad95c8266e724cd1983c031f07fd70b4016b25034b454d31784d2dff6f93 +size 342752960 diff --git a/FastThink-0.5B-Tiny.i1-IQ3_S.gguf b/FastThink-0.5B-Tiny.i1-IQ3_S.gguf new file mode 100644 index 0000000..e59da07 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccb2fe413ac0ac2e6853f809c74235309f2af8aa0cfef4bbb4954f8db595f85 +size 338608064 diff --git a/FastThink-0.5B-Tiny.i1-IQ3_XS.gguf b/FastThink-0.5B-Tiny.i1-IQ3_XS.gguf new file mode 100644 index 0000000..937e651 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbf87a7978b5bbcbc6124669d28c521b45a9ddef539d49b906c4f1f50909997d +size 338608064 diff --git a/FastThink-0.5B-Tiny.i1-IQ3_XXS.gguf b/FastThink-0.5B-Tiny.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6e37013 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de3a9de0e963f6abc4d8a8c044f229647eed2fb5c9f55af37847c9e5d31a49a9 +size 333705152 diff --git a/FastThink-0.5B-Tiny.i1-IQ4_NL.gguf b/FastThink-0.5B-Tiny.i1-IQ4_NL.gguf new file mode 100644 index 0000000..03f8262 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbe8ae5a2610084aeb2135d9104a48a8d9b233f2e99cf24f149094d8350f5041 +size 352671680 diff --git a/FastThink-0.5B-Tiny.i1-IQ4_XS.gguf b/FastThink-0.5B-Tiny.i1-IQ4_XS.gguf new file mode 100644 index 0000000..fafca35 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4fe8bb6748c40879cc0d023fa6767daa3f35d5a663ebaf0693dd1befabe691f +size 349403072 diff --git a/FastThink-0.5B-Tiny.i1-Q2_K.gguf b/FastThink-0.5B-Tiny.i1-Q2_K.gguf new file mode 100644 index 0000000..45d0d1a --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43005e765ba59769bdd3cf24d5998f22075c6f254f5b4471bc67e4300355f5c4 +size 338608064 diff --git a/FastThink-0.5B-Tiny.i1-Q2_K_S.gguf b/FastThink-0.5B-Tiny.i1-Q2_K_S.gguf new file mode 100644 index 0000000..9917f1c --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570110dddd8a3cbf21b58d9726df113ff623d9024b55f3c7567deda125719e80 +size 331049408 diff --git a/FastThink-0.5B-Tiny.i1-Q3_K_L.gguf b/FastThink-0.5B-Tiny.i1-Q3_K_L.gguf new file mode 100644 index 0000000..df65829 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9da561dba86e4519aa4bcca5c717e8b81fb0bc7a6ea64e700ffc30d8a2b96337 +size 369358784 diff --git a/FastThink-0.5B-Tiny.i1-Q3_K_M.gguf b/FastThink-0.5B-Tiny.i1-Q3_K_M.gguf new file mode 100644 index 0000000..ddf39c8 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1feb83196fa1770803adc44ff2d15b9faf3eec777a317116393d4ae16187f360 +size 355467200 diff --git a/FastThink-0.5B-Tiny.i1-Q3_K_S.gguf b/FastThink-0.5B-Tiny.i1-Q3_K_S.gguf new file mode 100644 index 0000000..139cfa3 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dcbf2fe4f18ada62fd8fccc74cdabec726d747c0422cb321b83feb3acaa93e3 +size 338264000 diff --git a/FastThink-0.5B-Tiny.i1-Q4_0.gguf b/FastThink-0.5B-Tiny.i1-Q4_0.gguf new file mode 100644 index 0000000..985c104 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591ed1eaf185d326d0d47eec04e174e63cb800d3c2fde8ed6b02f879eb5f9421 +size 352972736 diff --git a/FastThink-0.5B-Tiny.i1-Q4_1.gguf b/FastThink-0.5B-Tiny.i1-Q4_1.gguf new file mode 100644 index 0000000..a8be3a5 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67227804bcbd4a93018e09693062bea9fc2df9329450725a85874e6aa139a1da +size 374519744 diff --git a/FastThink-0.5B-Tiny.i1-Q4_K_M.gguf b/FastThink-0.5B-Tiny.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0de2112 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed21008560126e77238c3258018cf165e9d20a9ab3ef1343da44dec540e54b5e +size 397808576 diff --git a/FastThink-0.5B-Tiny.i1-Q4_K_S.gguf b/FastThink-0.5B-Tiny.i1-Q4_K_S.gguf new file mode 100644 index 0000000..cc3c8ba --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e94e1ad8a8de44be764641423f74a0f896b654cdc67e5dd3f773a69ce3fc7aa +size 385472448 diff --git a/FastThink-0.5B-Tiny.i1-Q5_K_M.gguf b/FastThink-0.5B-Tiny.i1-Q5_K_M.gguf new file mode 100644 index 0000000..de9a56c --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfcfd50d4d6f63e43280d46a90025e97c440b3fc49beb9016fe7d5b0039ee2f1 +size 420086720 diff --git a/FastThink-0.5B-Tiny.i1-Q5_K_S.gguf b/FastThink-0.5B-Tiny.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a9383a8 --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68ff89a7ddd01d215bbaa6f237de6107fb0d248b2017bc56ee28fd1ce1d7e2af +size 412710848 diff --git a/FastThink-0.5B-Tiny.i1-Q6_K.gguf b/FastThink-0.5B-Tiny.i1-Q6_K.gguf new file mode 100644 index 0000000..f7f11ce --- /dev/null +++ b/FastThink-0.5B-Tiny.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91585cb7977037e424a90e35b6c589c554c496b3c62a2c81503896f6a0f9fa3 +size 505737152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1646643 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: prithivMLmods/FastThink-0.5B-Tiny +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- Reasoner +- cot +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prithivMLmods/FastThink-0.5B-Tiny + + +static quants are available at https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-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/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/FastThink-0.5B-Tiny-i1-GGUF/resolve/main/FastThink-0.5B-Tiny.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..71a25c9 Binary files /dev/null and b/imatrix.dat differ