commit 2d75ad0d8ae7df3c437d83d1eadcd90ba5a01c12 Author: ModelHub XC Date: Thu May 14 18:24:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4dd85ec --- /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-Fusion-6040.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Fusion-6040.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ1_M.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ1_M.gguf new file mode 100644 index 0000000..4a6b996 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b8219231600294c2a6430ddfcc77ac2c5fffdb3a5f0fd7eb65ef01c0fb4c1b +size 2161973216 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ1_S.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ1_S.gguf new file mode 100644 index 0000000..394f953 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d1123bece7d2b1bee87a9e0cc436b6fd641b258824bb11dc44866d6393d435 +size 2019629024 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ2_M.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ2_M.gguf new file mode 100644 index 0000000..0606e81 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97b657935c326a8fe66aaae6017d38ba362096d067df710ca41d7c7b251f7e7 +size 2948282336 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ2_S.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ2_S.gguf new file mode 100644 index 0000000..0b2a69a --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e9900b7b256efaed0041623400a4cf4999cc37fd2c7c96a157114db753a93e9 +size 2758490080 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ2_XS.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b7aa40c --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968da8180615e69428766a3651c953887bf15e2ffc7864c9399a4f867d2a22aa +size 2605783008 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ2_XXS.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3027e0f --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9452347e9737f1fa81c4821a03a5ac162a3a7e84a3219dba9969071b51dd24 +size 2399213536 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ3_M.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ3_M.gguf new file mode 100644 index 0000000..0588005 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0472a7ad153af7ebefde3e0ac81acd1ec4c3ab06a99e88863d44df555bcd1855 +size 3784824800 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ3_S.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ3_S.gguf new file mode 100644 index 0000000..be2f151 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6226e49278359bf331aa3e6e3630cb8175a2cd3b51501e0ae7cae877239cef2e +size 3682326496 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ3_XS.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ3_XS.gguf new file mode 100644 index 0000000..8e64bfb --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019e9f23b9c0eb6d3a8667f08d26c4bac8ebe42e4680ff092201eb4540dbd8ad +size 3518748640 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ3_XXS.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..a6f4a06 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2809e814c8e6c5518e195cbf05443329a0fe302c6a7214e2d63fbb3de570318 +size 3274913760 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ4_NL.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ4_NL.gguf new file mode 100644 index 0000000..328ef2e --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c12d58c725dfcfdea83f7bf6e1d34be10558500523b613a42c81359500f72822 +size 4677990368 diff --git a/Llama-3.1-8B-Fusion-6040.i1-IQ4_XS.gguf b/Llama-3.1-8B-Fusion-6040.i1-IQ4_XS.gguf new file mode 100644 index 0000000..449a2f4 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c165e3c0a6dc0953c2034575d4a2eb77b560dc2380957d827064735a194b1bf +size 4447664096 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q2_K.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q2_K.gguf new file mode 100644 index 0000000..0c49b6c --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37fc40259e8fac95dcb5eb4d813349cac02f588f3d98f12205dc6f2f5bfabe2c +size 3179132896 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q2_K_S.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f686ec9 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfebe5980e57459a2b87c3b3105e726157f0d6a0c3828f34cff1f7355fd741b2 +size 2988816352 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q3_K_L.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q3_K_L.gguf new file mode 100644 index 0000000..fddf964 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cf5a37944fb49f28e392fcd519934cac61127cc89a44869e3b06b512afd3860 +size 4321957856 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q3_K_M.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q3_K_M.gguf new file mode 100644 index 0000000..95c0fa5 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:723132480e6911eba91a1421cb8ebe81858292f6a17d4a60382ecaa47d497a63 +size 4018919392 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q3_K_S.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q3_K_S.gguf new file mode 100644 index 0000000..42c1a81 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe18ae8fda2ba79c5cbf2d9184df0d53179fbd38f933b8b875679c6b9ff9ffd +size 3664500704 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q4_0.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q4_0.gguf new file mode 100644 index 0000000..c54a572 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1699e84b1e5e7d00cdbb407087b777f66eb1b1ecc1bd336d591395ea634f0176 +size 4675893216 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q4_1.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q4_1.gguf new file mode 100644 index 0000000..aa02705 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25329e383146916b117403939665bce5edcd639baa146738cbaf67fee01f804b +size 5130254304 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q4_K_M.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ca6b09b --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3625de69ff649354f209454f513ac9624ad2131da0434027b6398f19ec671598 +size 4920735712 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q4_K_S.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q4_K_S.gguf new file mode 100644 index 0000000..1cf8ba5 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee4c58f4370a973bd5e2f373529332394b48621fcdfda17b73d80e1e3a33436 +size 4692670432 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q5_K_M.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q5_K_M.gguf new file mode 100644 index 0000000..2412b30 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8e13ba81c52092de136051a97d44a033a276b82050d25f8b39bdccab95152e +size 5732988896 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q5_K_S.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q5_K_S.gguf new file mode 100644 index 0000000..79d4b37 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c3dea5d6468d3f620535bb2f8c0a26d08f70f2e56d3565e3a674487790d74d +size 5599295456 diff --git a/Llama-3.1-8B-Fusion-6040.i1-Q6_K.gguf b/Llama-3.1-8B-Fusion-6040.i1-Q6_K.gguf new file mode 100644 index 0000000..a701181 --- /dev/null +++ b/Llama-3.1-8B-Fusion-6040.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296087b97f93dcb14401dc5b5446ac2d893648c3d283d156e12bf2f9449ea09f +size 6596007904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..69c07ca --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: huihui-ai/Llama-3.1-8B-Fusion-6040 +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Text Generation +- llama3.1 +- text-generation-inference +- Inference Endpoints +- Transformers +- Fusion +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/huihui-ai/Llama-3.1-8B-Fusion-6040 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-Fusion-6040-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-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-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Fusion-6040-i1-GGUF/resolve/main/Llama-3.1-8B-Fusion-6040.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..2efa65c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f974ef24f025478a7289f5db4e26b2bd3e82e82ae3d94d6563318f7f48b4a3 +size 4988157