commit 2b3b9526bb5a54a5c085be8d3c2e9ec17b7d3a1a Author: ModelHub XC Date: Thu May 14 01:28:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..561414e --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Reason-Blend-888k.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_M.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_M.gguf new file mode 100644 index 0000000..950268c --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcbf10b068165c96bebcbb629367adb298e913b4bcab5f7951ec63016f3d616f +size 2161978688 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_S.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_S.gguf new file mode 100644 index 0000000..99c6b4c --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2fb24ef8c48fe803d1aaee8811086dde40c536b0863d06b9f65c65761d7743 +size 2019634496 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_M.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_M.gguf new file mode 100644 index 0000000..776c067 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5611a3a1e286a137ea3c299a3a0933a0fb1d0e26927850c435b11310182accc +size 2948287808 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_S.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_S.gguf new file mode 100644 index 0000000..df97dff --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:241b78ce2859d61c183f3b0e66eeaccdd531a14fc3759894ed3b20ea93b24144 +size 2758495552 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XS.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..12f51b2 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d21d82dd3071907872b6c6067d0015533a7e47fc9632584d4d56acb0917d2169 +size 2605788480 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XXS.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..47f4159 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a554e0764c5d769fbb5e0e23228bc37b21211b37d05834e45a0c97ba490d3643 +size 2399219008 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_M.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_M.gguf new file mode 100644 index 0000000..3613115 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f9fafb1b39ad2e5e109223549bafcd2c71b726966482a46e28a6c3e82cc0255 +size 3784830272 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_S.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_S.gguf new file mode 100644 index 0000000..a71a7ac --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751df5f72c7dc7aef90260a43f83230f7aa87addb6e5ebf2b96ce8f0fb1e08be +size 3682331968 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XS.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d1313e8 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:300c17f1fe975c2c62608cc02c8104434e9dae2fec20a7ff82670176fe817bbd +size 3518754112 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XXS.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..cf9bac2 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e324271c185d17dac1b8ce35b6d03c8d6a26ef2372ff9d6119540a4b611537e +size 3274919232 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_NL.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_NL.gguf new file mode 100644 index 0000000..6c6b0e2 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7ea56f497677eb584375789f992b2e2fc52ced51b3157f98c6670d5c0a3242 +size 4677995840 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_XS.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..20fc86a --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e63be4b839a69466daa5a04c9d1bfa6ea0f5a10a137b4599244d6daf019ab67 +size 4447669568 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K.gguf new file mode 100644 index 0000000..ffe0513 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c21ca428981d0f9beef7d33658de1aab9309a77085a76ac7064f2e4720127247 +size 3179138368 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K_S.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f416cbb --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd668c039b7c08310390cbb4db186bf21d2aeefe9e7d4cc29c16403c8da3737 +size 2988821824 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_L.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..53b487e --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77d83960a77d40209bcd77e2a25607d2c09a1d5fb855843f9603cb238fe0b11 +size 4321963328 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_M.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..b17ca07 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbeb94011740e1254546a5f07a7153b0943fd7d30e5e8f5871a23663f98612f8 +size 4018924864 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_S.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d84673e --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a4a32e52cb8004e60b5303ac9b15698ac416bb33cc812c2c132932e4fc52cb +size 3664506176 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_0.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_0.gguf new file mode 100644 index 0000000..3251641 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4a6508ba97ef621b2038937f288785f9b9999f4dd1e3b6601db6880756e826 +size 4675898688 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_1.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_1.gguf new file mode 100644 index 0000000..662d279 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15bb7ca1bb2ef9271d560c09331f845ff285e909329b3c2bd2260dc7eff3c307 +size 5130259776 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_M.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e3c3532 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8eb9fda7d4f14823109e5a23d1a206c462f4c46ea84af54c553f52bab4c1ecd +size 4920741184 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_S.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2cfd065 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4e54a3239993a03dbdfcffea943f89195badb2ad7ee975b1cfc101d5c2bf89 +size 4692675904 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_M.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7534cf2 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c5f32fbe0f8a1bd94b093d1c0baa24ffae6b76ba085bf944d93da890205116 +size 5732994368 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_S.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..4f27a8d --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba15cc6ed46428cb7ff038607e0dd733eed2fe535492a592f87a0900f6f7abe +size 5599300928 diff --git a/Llama-3.1-8B-Reason-Blend-888k.i1-Q6_K.gguf b/Llama-3.1-8B-Reason-Blend-888k.i1-Q6_K.gguf new file mode 100644 index 0000000..6cc1e10 --- /dev/null +++ b/Llama-3.1-8B-Reason-Blend-888k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50adb7eb4786392938336caf674b64a7ca4d7c6e81f3fe3053bb347eae962b6b +size 6596013376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..202cd08 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: khulaifi95/Llama-3.1-8B-Reason-Blend-888k +datasets: +- mlabonne/orca-agentinstruct-1M-v1-cleaned +- HuggingFaceTB/smoltalk +- Magpie-Align/Magpie-Qwen2.5-Pro-300K-Filtered +- Magpie-Align/Magpie-Qwen2-Pro-200K-Chinese +- O1-OPEN/OpenO1-SFT +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/khulaifi95/Llama-3.1-8B-Reason-Blend-888k + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-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-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Reason-Blend-888k-i1-GGUF/resolve/main/Llama-3.1-8B-Reason-Blend-888k.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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..ca2b8a5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d119df3fd226d0bcd0bb9555b13e370d21f405f4cdc81815ae6b7123a0972a +size 4988157