๐ Model Description
license: apache-2.0 language:
- ja
- TFMC/imatrix-dataset-for-japanese-llm
- tokyotech-llm/GPT-OSS-Swallow-20B-SFT-v0.1
GPT-OSS-Swallow-20B-SFT-v0.1-gguf
tokyotech-llmใใใๅ ฌ้ใใฆใใGPT-OSS-Swallow-20B-SFT-v0.1ใฎggufใใฉใผใใใๅคๆ็ใงใใimatrixใฎใใผใฟใฏTFMC/imatrix-dataset-for-japanese-llmใไฝฟ็จใใฆไฝๆใใพใใใ
Usage
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build --config Release
build/bin/llama-cli -m 'GPT-OSS-Swallow-20B-SFT-v0.1-gguf' -n 128 -c 128 -p 'ใใชใใฏใใญใฎๆ็ไบบใงใใใฌใทใใๆใใฆ' -cnv๐ GGUF File List
| ๐ Filename | ๐ฆ Size | โก Download |
|---|---|---|
|
GPT-OSS-Swallow-20B-SFT-v0.1-IQ3_M.gguf
LFS
Q3
|
11.36 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-IQ4_NL.gguf
LFS
Q4
|
11.27 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-IQ4_XS.gguf
LFS
Q4
|
11.27 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-MXFP4_MOE.gguf
LFS
|
11.28 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q3_K_L.gguf
LFS
Q3
|
12.42 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q3_K_M.gguf
LFS
Q3
|
12.03 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q4_0.gguf
Recommended
LFS
Q4
|
11.27 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q4_K_M.gguf
LFS
Q4
|
14.72 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q4_K_S.gguf
LFS
Q4
|
13.65 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q5_0.gguf
LFS
Q5
|
13.63 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q5_K_M.gguf
LFS
Q5
|
15.73 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q5_K_S.gguf
LFS
Q5
|
14.8 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q6_K.gguf
LFS
Q6
|
20.67 GB | Download |
|
GPT-OSS-Swallow-20B-SFT-v0.1-Q8_0.gguf
LFS
Q8
|
20.73 GB | Download |