commit bcc301bd01779079a00d6c256297d2c31cd505c8 Author: ModelHub XC Date: Sat Jun 13 22:04:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0d0ec95 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-3.2-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-8B-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-8B-Instruct.IQ4_XS.gguf b/Llama-3.2-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..123ceca --- /dev/null +++ b/Llama-3.2-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b31d227f087690e9ba9d7ef637a0272326d41f6133c3961dde622757d6af40 +size 4484367776 diff --git a/Llama-3.2-8B-Instruct.Q2_K.gguf b/Llama-3.2-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..30d52e7 --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:550f28668f22974b8573bcd08438e5190493d05b2c676cf08e2346b25d7e9284 +size 3179136416 diff --git a/Llama-3.2-8B-Instruct.Q3_K_L.gguf b/Llama-3.2-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..4f1f5c4 --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f68e3350055c92fab77a8b62d6dbbb273ffcf6de76ab04661d4f41bef3ef508c +size 4321961376 diff --git a/Llama-3.2-8B-Instruct.Q3_K_M.gguf b/Llama-3.2-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..96175ae --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9eb263acc9eac7175e244cdfcf5598b23888d0425bbe2516f8cc2f91791da9f +size 4018922912 diff --git a/Llama-3.2-8B-Instruct.Q3_K_S.gguf b/Llama-3.2-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..0086731 --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5001e87ed38aa99b1c9416d8a65ec500b33707c2f35d18a011261375c21c102 +size 3664504224 diff --git a/Llama-3.2-8B-Instruct.Q4_0_4_4.gguf b/Llama-3.2-8B-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..11b41ca --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43aa010b36fff3cd487e7bc482315ffbb19e0b63b461548e3585a04a05b3e9f5 +size 4661216672 diff --git a/Llama-3.2-8B-Instruct.Q4_K_M.gguf b/Llama-3.2-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f0bb921 --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee117efee146070318cc0d22f51b9282cb0f3e70cacf1f178bc6a820faea3a8 +size 4920739232 diff --git a/Llama-3.2-8B-Instruct.Q4_K_S.gguf b/Llama-3.2-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..d4cb79f --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c345d8ae5b98fad1455998e84dd095d93eddf2e0d2fd30c4d1429bb0686c4a64 +size 4692673952 diff --git a/Llama-3.2-8B-Instruct.Q5_K_M.gguf b/Llama-3.2-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..04f4fe6 --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf32d9d093db45f75b1a38fef88eab2d9aff6d22f2691010d4a44c81c445711 +size 5732992416 diff --git a/Llama-3.2-8B-Instruct.Q5_K_S.gguf b/Llama-3.2-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..a7d94a5 --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69204b2c29c31ae8e6ef30c0b7eae2fa22049f1a1c1852a14a02ab0042ac0ae1 +size 5599298976 diff --git a/Llama-3.2-8B-Instruct.Q6_K.gguf b/Llama-3.2-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..c3002f1 --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:babdde373f770e81d0919e22af11dbbca65efe937347615497441d357af81807 +size 6596011424 diff --git a/Llama-3.2-8B-Instruct.Q8_0.gguf b/Llama-3.2-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..92b1a13 --- /dev/null +++ b/Llama-3.2-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c77cf68d6d735616dfc32255cc89660ddee5afde26a2491daf405d05478727d +size 8540775840 diff --git a/Llama-3.2-8B-Instruct.f16.gguf b/Llama-3.2-8B-Instruct.f16.gguf new file mode 100644 index 0000000..371d583 --- /dev/null +++ b/Llama-3.2-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3076d67098778afca1e888be753e829566105efed3609cc1bc15a9666e0e5129 +size 16068896160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b7e947d --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: voidful/Llama-3.2-8B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/voidful/Llama-3.2-8B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-i1-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-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-8B-Instruct-GGUF/resolve/main/Llama-3.2-8B-Instruct.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +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. + +