commit 26b44598a3e6b3798608380376a52c40fd3c71f7 Author: ModelHub XC Date: Wed May 6 19:52:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ec155a --- /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 +Llama3.1-8B-Thinking-R1.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ1_M.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ1_M.gguf new file mode 100644 index 0000000..76af4e3 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e28d0ec9425b6b940f52c63517324687938fec81953d5fad4ba9c81d50f2ba +size 2161977568 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ1_S.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ1_S.gguf new file mode 100644 index 0000000..f45b58d --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba8abafbabbfcdf2120e16c43f7c3ec4a391fd1e12bcef2b1281443ad8ef4db1 +size 2019633376 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ2_M.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ2_M.gguf new file mode 100644 index 0000000..8ce72e9 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50917f1cd65e906b471a7a8db093e45b316d90e15b610dfccf4be73851e9737b +size 2948286688 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ2_S.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ2_S.gguf new file mode 100644 index 0000000..1cc262d --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dbf4cb7273836ca98a688a1ebeb05d0127cedd5228ec207a6f87df6e9306e36 +size 2758494432 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ2_XS.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..1bf4bfe --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbdb8d8550b5b34d654102507f52f28012c0195ce3bd54ce453cff5906e989cc +size 2605787360 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ2_XXS.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..995762b --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb5f6d06e3604ecfd7b455835258d9e49c5fd6e8d181c275fe9eae5e699954f +size 2399217888 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ3_M.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ3_M.gguf new file mode 100644 index 0000000..fe16ff4 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db25cf28136afa01c80df1dff89be87e90a4c4ddb6b1183bdd0e26c12e2c755b +size 3784829152 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ3_S.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ3_S.gguf new file mode 100644 index 0000000..d3856fa --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb1275c7c415e395f11c1c4da42ff0e96875f189182a9cd29905eba2b2e9365a +size 3682330848 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ3_XS.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2d6f20a --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9681f0b0fb3f1f0fb07726f6be5b2420260be9a8cbd1be3e6b3151efaddfb2 +size 3518752992 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ3_XXS.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..de42a84 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbeba364057907e601316a6d91e9f2b97e36fb45452a93ec749a065ab3c51e10 +size 3274918112 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ4_NL.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..eb8c66f --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f13bfd3d84a523620ce752e9dccfd3ea9134ef6fc301bd6571c3f8095b861ea7 +size 4677994720 diff --git a/Llama3.1-8B-Thinking-R1.i1-IQ4_XS.gguf b/Llama3.1-8B-Thinking-R1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9a5a486 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872c3f91de1cb3fc1bef5d67252ec0570db44994b5250c3b00ff90a741c3beae +size 4447668448 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q2_K.gguf b/Llama3.1-8B-Thinking-R1.i1-Q2_K.gguf new file mode 100644 index 0000000..7eebd2b --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2107fde623f6f717ee5945b206a82ddd8c7683eecdd395e862fc73beb72ca6ba +size 3179137248 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q2_K_S.gguf b/Llama3.1-8B-Thinking-R1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4e165ac --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6640b3b3c499cb51b85828156907709184092c37c2007bf97c1d2fa068b8e24 +size 2988820704 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q3_K_L.gguf b/Llama3.1-8B-Thinking-R1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f570a44 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8858ab949c6a4aa567658a9ccff530f591739537ab990f8a75364385acb49cfe +size 4321962208 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q3_K_M.gguf b/Llama3.1-8B-Thinking-R1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..042ee15 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428b50225d988b323dbee00fcb8d2e0d786aa23cbf0e526132daf0375544c22e +size 4018923744 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q3_K_S.gguf b/Llama3.1-8B-Thinking-R1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..976df3a --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef87837b0993a8a7013bf1069d750eb637320fd5ec27a96bcd4a7532d726eb05 +size 3664505056 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q4_0.gguf b/Llama3.1-8B-Thinking-R1.i1-Q4_0.gguf new file mode 100644 index 0000000..46f1472 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c664ae25cf9decf9aa1b2d6600c901ceb23cf3930886118ec6e8b9e9ad2f29dc +size 4675897568 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q4_1.gguf b/Llama3.1-8B-Thinking-R1.i1-Q4_1.gguf new file mode 100644 index 0000000..a080082 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf1f591820b19066011c03893c04b02e1951caa6612235f06d80f9fe6fb3687 +size 5130258656 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q4_K_M.gguf b/Llama3.1-8B-Thinking-R1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..13c6728 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3fc3e4feda9df83a7219d3ae128f29bfdaa67429fe4965ba7da4310c7a2cda0 +size 4920740064 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q4_K_S.gguf b/Llama3.1-8B-Thinking-R1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..e9536c1 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0603c511e551c011ed963314eb5969192bddb9f25154ee15a47f5f0de999d633 +size 4692674784 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q5_K_M.gguf b/Llama3.1-8B-Thinking-R1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..955c9f5 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c303f8fe711aebe4470d79c325923618da0ee83506cf29be3287b28e6f6826fa +size 5732993248 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q5_K_S.gguf b/Llama3.1-8B-Thinking-R1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..106e92d --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011df063bbc4fccbcd30d5fed0fa9e1c4b3712cc4122b32f909d04ff2285b71f +size 5599299808 diff --git a/Llama3.1-8B-Thinking-R1.i1-Q6_K.gguf b/Llama3.1-8B-Thinking-R1.i1-Q6_K.gguf new file mode 100644 index 0000000..adc3e40 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b290399788d1cdad2be892a4ab873aa62502d49f9c0366bc6d8357822151a1f +size 6596012256 diff --git a/Llama3.1-8B-Thinking-R1.imatrix.gguf b/Llama3.1-8B-Thinking-R1.imatrix.gguf new file mode 100644 index 0000000..dd41188 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51da5d35da4fca10f817fb8f248a55656555cd8554c36b7ac39ee32ab63e508a +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ab182e --- /dev/null +++ b/README.md @@ -0,0 +1,99 @@ +--- +base_model: Jackrong/Llama3.1-8B-Thinking-R1 +datasets: +- unsloth/OpenMathReasoning-mini +- open-r1/DAPO-Math-17k-Processed +- Jackrong/ShareGPT-gpt-oss-120B-reasoning +- Jackrong/Chinese-Qwen3-235B-Thinking-Distill +- Jackrong/MultiReason-ChatAlpaca +language: +- en +- zh +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reasoning +- thinking +- grpo +- r1 +- llama-cpp +- gguf +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Jackrong/Llama3.1-8B-Thinking-R1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-8B-Thinking-R1-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-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/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.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. + +