commit f4e06ab4264b42d1fd2de77a8b47d8607f50abf5 Author: ModelHub XC Date: Sun Oct 4 08:07:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-6B-v0.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..92eb666 --- /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-3-6B-v0.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-v0.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-6B-v0.1.i1-IQ1_M.gguf b/Llama-3-6B-v0.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..36783d1 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6a0b041d2d0940f26c61edfb33529bd47ca7b7c8198e6607d97ed30ba3837d +size 1756825024 diff --git a/Llama-3-6B-v0.1.i1-IQ1_S.gguf b/Llama-3-6B-v0.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..4c70d19 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedc9fa96a6c6baf5d3a9185b5d084bdfedee44b3e487c8352771cc21c850f66 +size 1650066880 diff --git a/Llama-3-6B-v0.1.i1-IQ2_M.gguf b/Llama-3-6B-v0.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..0d40fcf --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c4455289657779675ffe96c91da1250632da40418ffaa9811d89bd416b80da +size 2359895488 diff --git a/Llama-3-6B-v0.1.i1-IQ2_S.gguf b/Llama-3-6B-v0.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..d53d183 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d298a46c6bbe964ed029aa2499fceee07ff8fd88312cea6fac9e91c4f392c2c +size 2217551296 diff --git a/Llama-3-6B-v0.1.i1-IQ2_XS.gguf b/Llama-3-6B-v0.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..e741c33 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610ed5a95e04e79d2b7f72bb78d705e5171d1c0bc771427cc1f0754ae14e7ec8 +size 2089682368 diff --git a/Llama-3-6B-v0.1.i1-IQ2_XXS.gguf b/Llama-3-6B-v0.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..3e8574f --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b68e38dc45905a1d7fbf275b433e20f5f95ef0f09379fea09b6ad75e95d68046 +size 1934755264 diff --git a/Llama-3-6B-v0.1.i1-IQ3_M.gguf b/Llama-3-6B-v0.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..437addf --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4cd4e32075d52d0a6fb392bee41fc1572eb90918a916c2c9e71c604c2d6b6f2 +size 3004745152 diff --git a/Llama-3-6B-v0.1.i1-IQ3_S.gguf b/Llama-3-6B-v0.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..7da3784 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fabaed0ce2dbc98e996dc00552fb7110c63d43fa0a9841776447c381c99a5af8 +size 2927871424 diff --git a/Llama-3-6B-v0.1.i1-IQ3_XS.gguf b/Llama-3-6B-v0.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0b19ec0 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de134c21ba0620c13a2996ec979055221e3e7a530df111ea721e1bf9e1832fb8 +size 2805188032 diff --git a/Llama-3-6B-v0.1.i1-IQ3_XXS.gguf b/Llama-3-6B-v0.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..987e845 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b2b770e62777d316f33e5341b12f18813b4573b8301638a7fa35a52ff4f80b1 +size 2604869056 diff --git a/Llama-3-6B-v0.1.i1-IQ4_NL.gguf b/Llama-3-6B-v0.1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..0f2787a --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6107b8060a51652ed5b23936f024feb3d9f3985fe62c99cbb12f6756add9b10 +size 3692062144 diff --git a/Llama-3-6B-v0.1.i1-IQ4_XS.gguf b/Llama-3-6B-v0.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..6a7841d --- /dev/null +++ b/Llama-3-6B-v0.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54de69ebdbe0ccfd9e7bb2477fa657d21aaacc98fde4dba497864676273c2b91 +size 3515213248 diff --git a/Llama-3-6B-v0.1.i1-Q2_K.gguf b/Llama-3-6B-v0.1.i1-Q2_K.gguf new file mode 100644 index 0000000..a872a0b --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad744ba51877f11d3be0432a296328aab4e471f92fe392add88df3406df9cee6 +size 2537137600 diff --git a/Llama-3-6B-v0.1.i1-Q2_K_S.gguf b/Llama-3-6B-v0.1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..be7afaa --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5630bb4b05431c58deb0e14aa6ff3acabec16a66e0b67c0cf10ff5829ca7cd41 +size 2394400192 diff --git a/Llama-3-6B-v0.1.i1-Q3_K_L.gguf b/Llama-3-6B-v0.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..cfbd031 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc503d7d262ffac0a2467a7502027c5b4c001455d308cbe31b846c0fa9ebbec +size 3407594944 diff --git a/Llama-3-6B-v0.1.i1-Q3_K_M.gguf b/Llama-3-6B-v0.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..ad9e17f --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9586208be887596aa505ff5ec9b8d9953c5be4431c5b6954e96539f2d81e41b1 +size 3176908224 diff --git a/Llama-3-6B-v0.1.i1-Q3_K_S.gguf b/Llama-3-6B-v0.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..4873900 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1cfde2c9f382feb789e13e686bb270a6f929d31db27cebd387c7e2d3fe4ead0 +size 2914502080 diff --git a/Llama-3-6B-v0.1.i1-Q4_0.gguf b/Llama-3-6B-v0.1.i1-Q4_0.gguf new file mode 100644 index 0000000..371490b --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d27914f2c25e52da10907cb02088b641781c180a263652b871c89f320254fdc +size 3690489280 diff --git a/Llama-3-6B-v0.1.i1-Q4_1.gguf b/Llama-3-6B-v0.1.i1-Q4_1.gguf new file mode 100644 index 0000000..05dd633 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1058056658b8a52891f4a5b233162687bba87d7fe67a1fcdba1943f3abde4551 +size 4039468480 diff --git a/Llama-3-6B-v0.1.i1-Q4_K_M.gguf b/Llama-3-6B-v0.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e88f3e2 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4896f6b9f8ca016e27c928cae069db2cb2f5818305562cf6ca535f1ad383241a +size 3874121152 diff --git a/Llama-3-6B-v0.1.i1-Q4_K_S.gguf b/Llama-3-6B-v0.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..daaf95d --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b301fa6a5553416d59b48cd37b3c7ce01284d13ef5fe87f0b47e7a4475d49830 +size 3703596480 diff --git a/Llama-3-6B-v0.1.i1-Q5_K_M.gguf b/Llama-3-6B-v0.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..56b2a29 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47c815d6220fbc2c561718254a67e50fe51d32358477098fb6d90c7cbeaf2533 +size 4499727808 diff --git a/Llama-3-6B-v0.1.i1-Q5_K_S.gguf b/Llama-3-6B-v0.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b376fbe --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70f1253f79a763917a5a12c01f79c01e33790ff76600a20c373ec1e40d29911 +size 4399457728 diff --git a/Llama-3-6B-v0.1.i1-Q6_K.gguf b/Llama-3-6B-v0.1.i1-Q6_K.gguf new file mode 100644 index 0000000..bc3d270 --- /dev/null +++ b/Llama-3-6B-v0.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca835120f2ab0dfe4da60ebcf350311db3a42169589811bcab91812e190bb6d +size 5164434880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..06a4cf3 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: prince-canuma/Llama-3-6B-v0.1 +datasets: +- prince-canuma/fineweb-CC-MAIN-2024-10-1B-en +- HuggingFaceFW/fineweb +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- Llama-3-6B +- 6B +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/prince-canuma/Llama-3-6B-v0.1 + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-6B-v0.1-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/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 1.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 2.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 3.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 3.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 3.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q4_1.gguf) | i1-Q4_1 | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-v0.1-i1-GGUF/resolve/main/Llama-3-6B-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 5.3 | 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..8069317 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dced87a387f7a6adc9ccfd86a5413be1d32ebde2de5da71d796de25a3defa272 +size 3741109