commit 695ee01a13bdf179e14ce202d9a041e71b9d2abe Author: ModelHub XC Date: Mon May 11 10:39:42 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Heretic-Llama-Express.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..edfc130 --- /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 +Heretic-Llama-Express.1.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Heretic-Llama-Express.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Heretic-Llama-Express.1.i1-IQ1_M.gguf b/Heretic-Llama-Express.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..2bc18e2 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde03f668db71fde4fff5c87232ae35253ed983b5a0013accc708a156e0d3a26 +size 413607360 diff --git a/Heretic-Llama-Express.1.i1-IQ1_S.gguf b/Heretic-Llama-Express.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..0997809 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65450f3f11ce916ea6f7cada1e14e791e6f3f8f27638c1e93ab1d230b53590ac +size 393553344 diff --git a/Heretic-Llama-Express.1.i1-IQ2_M.gguf b/Heretic-Llama-Express.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..7505a64 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a4f49067c7177763f9d6078a91effdfdc75e7fb84d709e72a5cab7b493ddfd +size 515450304 diff --git a/Heretic-Llama-Express.1.i1-IQ2_S.gguf b/Heretic-Llama-Express.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..6c31e6f --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ab0fc0c2261380800eaa52ed915b7fc465db048b47505f053f7f47909429a9a +size 488711616 diff --git a/Heretic-Llama-Express.1.i1-IQ2_XS.gguf b/Heretic-Llama-Express.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..416cff0 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389b7756006642d4cf1a8a18475d03e8ac260f09d05dfaa6a0abae40181b839c +size 475866560 diff --git a/Heretic-Llama-Express.1.i1-IQ2_XXS.gguf b/Heretic-Llama-Express.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bc4e6c7 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c0b3677dd7190b0660d5db90fcffa99320ac0c49be338e5189ec3a00eab804 +size 447030720 diff --git a/Heretic-Llama-Express.1.i1-IQ3_M.gguf b/Heretic-Llama-Express.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..2e9d55f --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c059823fc5f9bb437d22d500c5fc7ee78406ee9f65b68a791ffb3f8d545f5e3a +size 657290688 diff --git a/Heretic-Llama-Express.1.i1-IQ3_S.gguf b/Heretic-Llama-Express.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..f899da3 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356d9f56d2856f41b5683d9f5fe842359d48256c4f84a2fb8a61ae4f5f50db6e +size 643921344 diff --git a/Heretic-Llama-Express.1.i1-IQ3_XS.gguf b/Heretic-Llama-Express.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..54fa4bc --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622966a68bf921285d8b54f0978d803dbdef2009dfe0f2fce6aa74b8e975b7a5 +size 621114816 diff --git a/Heretic-Llama-Express.1.i1-IQ3_XXS.gguf b/Heretic-Llama-Express.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..86fc2cf --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edc9b0d1a0f8094eafb5895f423c98ec33fd5df35a00a5bb7667aaf72ce1678c +size 562111936 diff --git a/Heretic-Llama-Express.1.i1-IQ4_NL.gguf b/Heretic-Llama-Express.1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..fb6c543 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e67559f080230388d7f5b0b652120c93767b522e5c51150f9017add2f34b30b +size 773027264 diff --git a/Heretic-Llama-Express.1.i1-IQ4_XS.gguf b/Heretic-Llama-Express.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..815775b --- /dev/null +++ b/Heretic-Llama-Express.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78aa68f52b55ab00eb8ccde92d6e65fde4f27d3161340549083428bdeee485f +size 743142848 diff --git a/Heretic-Llama-Express.1.i1-Q2_K.gguf b/Heretic-Llama-Express.1.i1-Q2_K.gguf new file mode 100644 index 0000000..4f79705 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961dfcbf376c0c31dca4ba64c9fa422448c40f3e366228ef258ddd625cd61929 +size 580875712 diff --git a/Heretic-Llama-Express.1.i1-Q2_K_S.gguf b/Heretic-Llama-Express.1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ec76d31 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6b8aa6cb764db12ebf203b2fca4ef16b9f3bda2dc68a9fcdc1cab5e1abddf3f +size 554661312 diff --git a/Heretic-Llama-Express.1.i1-Q3_K_L.gguf b/Heretic-Llama-Express.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..561a7e5 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b06658c609d3f0bbfb2545f5212a438e3002e4289ba2774733d0b78802d905 +size 732526016 diff --git a/Heretic-Llama-Express.1.i1-Q3_K_M.gguf b/Heretic-Llama-Express.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b4c08e9 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e89ac30d2e1db3e9a256e6683e66d24914ee335791f22ea026a6efc959f550e5 +size 690845120 diff --git a/Heretic-Llama-Express.1.i1-Q3_K_S.gguf b/Heretic-Llama-Express.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..6bd4c00 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be8cf9b0a52a2fc43896d88da993daf0c8a072837223ff601be5081fe5f804b +size 641693120 diff --git a/Heretic-Llama-Express.1.i1-Q4_0.gguf b/Heretic-Llama-Express.1.i1-Q4_0.gguf new file mode 100644 index 0000000..d8cb92a --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4a5405e471b829e5203df17b2d5bb5d425351f8a8efc61608ab5229f8a0af8 +size 773027264 diff --git a/Heretic-Llama-Express.1.i1-Q4_1.gguf b/Heretic-Llama-Express.1.i1-Q4_1.gguf new file mode 100644 index 0000000..ccafa99 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9077500b1a0ad4a6f05a480697181458a7b7ff794e8f9f919fdf10b6d6cd510c +size 831747520 diff --git a/Heretic-Llama-Express.1.i1-Q4_K_M.gguf b/Heretic-Llama-Express.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8cd9c04 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57531340054f0ed8c1d64719f9e9439e491b1929bdf83ed29c9c437afd49c605 +size 807695808 diff --git a/Heretic-Llama-Express.1.i1-Q4_K_S.gguf b/Heretic-Llama-Express.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9d73ca2 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c427b8f5d28b1fb64371947d706296e44f204daecf7e5dcacd21715e105eb05 +size 775648704 diff --git a/Heretic-Llama-Express.1.i1-Q5_K_M.gguf b/Heretic-Llama-Express.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..50f4811 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4666fe460cffeb663e57284a50f49a25b0ba7e8e376e956eb9c42ed69f750c3 +size 911504832 diff --git a/Heretic-Llama-Express.1.i1-Q5_K_S.gguf b/Heretic-Llama-Express.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..1aeefa7 --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c25d11e057c9bc29ba094eb2438dfcef9ce101f7ed3530138deb37bca720b34e +size 892564928 diff --git a/Heretic-Llama-Express.1.i1-Q6_K.gguf b/Heretic-Llama-Express.1.i1-Q6_K.gguf new file mode 100644 index 0000000..4d0c74d --- /dev/null +++ b/Heretic-Llama-Express.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79111adf7ef4e7f7bb7bd0073ac5f308d44e8d02008b76e82b95bfecd5b3e92b +size 1021801920 diff --git a/Heretic-Llama-Express.1.imatrix.gguf b/Heretic-Llama-Express.1.imatrix.gguf new file mode 100644 index 0000000..ad8ac28 --- /dev/null +++ b/Heretic-Llama-Express.1.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:186a4d7f7a3f6259cd02c4ee124e6f26606928b620b2f735cf7553a315d41ffd +size 1328000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..60035ad --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: hereticness/Heretic-Llama-Express.1 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/hereticness/Heretic-Llama-Express.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Heretic-Llama-Express.1-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Heretic-Llama-Express.1-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/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q4_1.gguf) | i1-Q4_1 | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Heretic-Llama-Express.1-i1-GGUF/resolve/main/Heretic-Llama-Express.1.i1-Q6_K.gguf) | i1-Q6_K | 1.1 | 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. + +