commit dcb98206660a8fd7ff87526d87d7652cdb2f2e46 Author: ModelHub XC Date: Tue Jul 28 09:01:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8b065bf --- /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 +LlamaMed-3.1-8B-Reasoner.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LlamaMed-3.1-8B-Reasoner.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ1_M.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ1_M.gguf new file mode 100644 index 0000000..e589484 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d3b1dbcb447eeb27da345b3474e9fb62ecaa66cd718e0a56598c3c026fea86a +size 2161977952 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ1_S.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ1_S.gguf new file mode 100644 index 0000000..dc0c0bd --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:377e2b1021f1fedef952fd9cb41f610c50d32b3415112883ae74481c0368b3f3 +size 2019633760 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ2_M.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ2_M.gguf new file mode 100644 index 0000000..3e1f5cc --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d82ee0ab97fe4f4a3f860fcaecaed81b463d7c704517605d0620babe0a2a1b +size 2948287072 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ2_S.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ2_S.gguf new file mode 100644 index 0000000..c3af045 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c485d0198df02571ffdd440a43eb6291e7b5b7078d258f2994b9dc336c49335f +size 2758494816 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ2_XS.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ2_XS.gguf new file mode 100644 index 0000000..7ac3756 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1985742f9ba28c2a58828e0f90c7fdfb7ab1da634e4ebed545529a7e0a3b66b9 +size 2605787744 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ2_XXS.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a85e75c --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9211729c11e9c861d8ae1d992b02ad5b8fff0f1c27e8f1a63b4eca539b1e09 +size 2399218272 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ3_M.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ3_M.gguf new file mode 100644 index 0000000..d527af8 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914697822d5df042cfaf262a046e05ea8ced28aeaeeca2054cc41e67868b2ffc +size 3784829536 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ3_S.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ3_S.gguf new file mode 100644 index 0000000..5af5d07 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa0772bf5b6aab9869b6be73f2493c4e7c19bb8dc8f5e808dd72884955b18ca1 +size 3682331232 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ3_XS.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ3_XS.gguf new file mode 100644 index 0000000..577ca9d --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e5cb37e205352beaf36200f08e44eaacb22fb55642e1babe72fe578d81151d +size 3518753376 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ3_XXS.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4053af0 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8410d3cb4c6e5000e06836bfc115d9e38b8b6a8b77107024e5e4e7e44de940 +size 3274918496 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ4_NL.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ4_NL.gguf new file mode 100644 index 0000000..be79a04 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee8069738049bf0c85463e15e991ac3a8feaaba6d14354857c0cbf982ba8cf34 +size 4677995104 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-IQ4_XS.gguf b/LlamaMed-3.1-8B-Reasoner.i1-IQ4_XS.gguf new file mode 100644 index 0000000..772d753 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ee6e0b3cf73c99ef6c9d20e53e5fd7a8978f10636183899be03f5010d4695a +size 4447668832 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q2_K.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q2_K.gguf new file mode 100644 index 0000000..1864080 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:714dccb67e6ec504a71508d5a7b3c90985f380bd8248a42f6e22a7a654f6a18c +size 3179137632 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q2_K_S.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7679e45 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2424d08a1726eaccb22c5aedcaa632475f19401b7b90e321d3226f47fc265ff2 +size 2988821088 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_L.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_L.gguf new file mode 100644 index 0000000..298ec10 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:993ad1438c922810a7926c3da6ab0888f580f6e6d0e8bd94c1da04f4895ba526 +size 4321962592 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_M.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4cc3217 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c92d54b4f057683b60a297945fdd21d3ffb0766d9dd93f78641a971359c4128 +size 4018924128 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_S.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6ba9a1b --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:493a3062556e640c440a9a7b4ac6148bdac042dc96e1121d80a076aa8bca7bbc +size 3664505440 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q4_0.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q4_0.gguf new file mode 100644 index 0000000..e415506 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f795bbb4987af7a7f34a020adf9a7e75cb5091dcc9ee3cd0176c917dd62eed70 +size 4675897952 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q4_1.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q4_1.gguf new file mode 100644 index 0000000..b509b01 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7fedc5d1a7b60aa1f369c48014f6ba98f8de50cb4c8f75a6b60ad514f37af6 +size 5130259040 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q4_K_M.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q4_K_M.gguf new file mode 100644 index 0000000..7be2f1c --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c943b677487c8545d38fce78704bebe023f51100c109e295582c0b04e65dc17 +size 4920740448 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q4_K_S.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q4_K_S.gguf new file mode 100644 index 0000000..914c27b --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d704459939f4d191bf5bb5a7af15125de7431c3b60467ced0ff994bc862cab +size 4692675168 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q5_K_M.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q5_K_M.gguf new file mode 100644 index 0000000..ec77332 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff98931f2d7a3ae1bbe85231c78b049a2732159d27d43b8ebd6ce61e9b88f9c +size 5732993632 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q5_K_S.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q5_K_S.gguf new file mode 100644 index 0000000..150e121 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae31821fccb2304a2ae04ac34bfe51bb289796d8339f5edbd83155c043ffcde5 +size 5599300192 diff --git a/LlamaMed-3.1-8B-Reasoner.i1-Q6_K.gguf b/LlamaMed-3.1-8B-Reasoner.i1-Q6_K.gguf new file mode 100644 index 0000000..8280b97 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41a8d8b7c48c38fec086605cdba8bd247bd2ba5bc5859069237cb91a4d72a94 +size 6596012640 diff --git a/LlamaMed-3.1-8B-Reasoner.imatrix.gguf b/LlamaMed-3.1-8B-Reasoner.imatrix.gguf new file mode 100644 index 0000000..1c26339 --- /dev/null +++ b/LlamaMed-3.1-8B-Reasoner.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6dc66aec256045ce349806a7e2832620d35eab95a64d8e60533d0d31b7171dc +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd66289 --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +base_model: Rumiii/LlamaMed-3.1-8B-Reasoner +datasets: +- lingshu-medical-mllm/ReasonMed +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- medical +- reasoning +- llama-3.1 +- reasonmed +- chain-of-thought +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/Rumiii/LlamaMed-3.1-8B-Reasoner + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LlamaMed-3.1-8B-Reasoner-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-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/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaMed-3.1-8B-Reasoner-i1-GGUF/resolve/main/LlamaMed-3.1-8B-Reasoner.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. + +