commit 03e0ab433feb046b5492c4a26db0988618ef3274 Author: ModelHub XC Date: Mon Oct 5 05:37:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e22a90 --- /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 +Llama-3.3-8B-Lumina-Reasoning.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_M.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_M.gguf new file mode 100644 index 0000000..639d210 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edc581f7c0480bea3d080957e29270df98ea4cf37003b7f2b7fa693a16c00bc9 +size 2161978272 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_S.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_S.gguf new file mode 100644 index 0000000..176be08 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2b8faedfd792f418e46b701d202d2922e34227fe29bd89e953033a035dbea37 +size 2019634080 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_M.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_M.gguf new file mode 100644 index 0000000..8bad379 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d2b9148b300796822187a1c7f69ec767bc7804bb3fd2d42634f9e5c0b69b3be +size 2948287392 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_S.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_S.gguf new file mode 100644 index 0000000..e556fb6 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e4475bfd811c09b875866ab845a4eb5f24fa34a7c1f89029bba7ff57cb584e4 +size 2758495136 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XS.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XS.gguf new file mode 100644 index 0000000..52d0d05 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a8f13d8e7128d897b938e1fc67eb48ea7b134aee77bf0a940ebd19d4288788 +size 2605788064 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XXS.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ac9594c --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa656ae81eb0bb5a87ca3ce130285293c1826a63e954b72fa31169e3b475dd0 +size 2399218592 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_M.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_M.gguf new file mode 100644 index 0000000..7eba6a2 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c16bc696f2684bbc9a3e722cf119e418882ca68bf103bae124cb871cda4f91 +size 3784829856 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_S.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_S.gguf new file mode 100644 index 0000000..302457d --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04580c55598d40fc262423eb4f4042124c7c6ae3a21e2029e145f378698b653f +size 3682331552 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XS.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XS.gguf new file mode 100644 index 0000000..bb35908 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074e7d6c48538441835f36ce439162366ba0885412a88f7dfb25b2429fe13bb0 +size 3518753696 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XXS.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..2a3e94b --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a77c50eb520333431ac55915e17649404cd5ed547587e6834a9a11c821e0fed +size 3274918816 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_NL.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_NL.gguf new file mode 100644 index 0000000..7bc1c71 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0514d4030beda297d3e737001d896567d5d8bd12534499af0eb15caa1af4fcdf +size 4677995424 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_XS.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_XS.gguf new file mode 100644 index 0000000..4c044be --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c706a52376f83af0351678f5690cc92b082fecb406d92dbe6bb0612e5daee70a +size 4447669152 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K.gguf new file mode 100644 index 0000000..9c1477d --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33260cff8adf26110e99b45d976930cd2ee4d5d32ad50d60762afd2dbe5f3d1c +size 3179137952 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K_S.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7c0e2c1 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30aa3d61b1575c5152a9a0d3cea0a056355bdb1b4b912b4ccc7dd3ed20c72e64 +size 2988821408 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_L.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_L.gguf new file mode 100644 index 0000000..699d963 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168938ed1a5f8a0eeef0284416a917882c710a1c2b100fe8964f4e49b584a536 +size 4321962912 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_M.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d37af0a --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275d2caef957e65ba9d3ed21f50fd702a623d8928c4ef538d53b9ca34f454b44 +size 4018924448 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_S.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e66da77 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadee6ae96466e70b8ad4c5eaed0141c7f4208c76c60482d23feace3c2f498ea +size 3664505760 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_0.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_0.gguf new file mode 100644 index 0000000..276e140 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349ee455986c961ed4f9723c1551d477e6dfabaabe6c2a16cbb0a8f46f3422d3 +size 4675898272 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_1.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_1.gguf new file mode 100644 index 0000000..aa93bb6 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d56660d2ab8e2e5cbf5d255af89fa02ea9106fa1f8e0aca8e6d3559218066d2 +size 5130259360 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_M.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_M.gguf new file mode 100644 index 0000000..28783a0 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0f227cb8358ccc8392924720fa3edc3393250be69588971622dd675e7f7eb6 +size 4920740768 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_S.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b625bf9 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb891dfdcc0f4d7f6819016133c0b0a5bd2d62f1e09baf48cc4858bb944ce61c +size 4692675488 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_M.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_M.gguf new file mode 100644 index 0000000..de82e5f --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2386d2ccf05003fc030fc43c56502c62bc2b9c92db53e9785376cc8af8f66f +size 5732993952 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_S.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_S.gguf new file mode 100644 index 0000000..c8ad2cb --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4259df631b11f948c2f9c0d04a159fd85beadc567920d193653e14ccc2ace2c3 +size 5599300512 diff --git a/Llama-3.3-8B-Lumina-Reasoning.i1-Q6_K.gguf b/Llama-3.3-8B-Lumina-Reasoning.i1-Q6_K.gguf new file mode 100644 index 0000000..79b11e2 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99495587f9457a36cd23ae96dad97c99641f02d1a14afb5c6a4d2d385d1c892a +size 6596012960 diff --git a/Llama-3.3-8B-Lumina-Reasoning.imatrix.gguf b/Llama-3.3-8B-Lumina-Reasoning.imatrix.gguf new file mode 100644 index 0000000..b51d4f9 --- /dev/null +++ b/Llama-3.3-8B-Lumina-Reasoning.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f599dc4f24c9933b9de79d6720bfc93ba75b2ee17751623057ffc8c25528831 +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..729056e --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: 0xA50C1A1/Llama-3.3-8B-Lumina-Reasoning +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/0xA50C1A1/Llama-3.3-8B-Lumina-Reasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-8B-Lumina-Reasoning-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-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/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-8B-Lumina-Reasoning-i1-GGUF/resolve/main/Llama-3.3-8B-Lumina-Reasoning.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. + +