You can deploy this model and start earning money today!

RichardErkhov/
owner203_-_japanese-llama-3-8b-instruct-v2-gguf

Name: owner203_-_japanese-llama-3-8b-instruct-v2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

japanese-llama-3-8b-instruct-v2 - GGUF

Name	Quant method	Size
japanese-llama-3-8b-instruct-v2.Q2_K.gguf	Q2_K	2.96GB
japanese-llama-3-8b-instruct-v2.IQ3_XS.gguf	IQ3_XS	3.28GB
japanese-llama-3-8b-instruct-v2.IQ3_S.gguf	IQ3_S	3.43GB
japanese-llama-3-8b-instruct-v2.Q3_K_S.gguf	Q3_K_S	3.41GB
japanese-llama-3-8b-instruct-v2.IQ3_M.gguf	IQ3_M	3.52GB
japanese-llama-3-8b-instruct-v2.Q3_K.gguf	Q3_K	3.74GB
japanese-llama-3-8b-instruct-v2.Q3_K_M.gguf	Q3_K_M	3.74GB
japanese-llama-3-8b-instruct-v2.Q3_K_L.gguf	Q3_K_L	4.03GB
japanese-llama-3-8b-instruct-v2.IQ4_XS.gguf	IQ4_XS	4.18GB
japanese-llama-3-8b-instruct-v2.Q4_0.gguf	Q4_0	4.34GB
japanese-llama-3-8b-instruct-v2.IQ4_NL.gguf	IQ4_NL	4.38GB
japanese-llama-3-8b-instruct-v2.Q4_K_S.gguf	Q4_K_S	4.37GB
japanese-llama-3-8b-instruct-v2.Q4_K.gguf	Q4_K	4.58GB
japanese-llama-3-8b-instruct-v2.Q4_K_M.gguf	Q4_K_M	4.58GB
japanese-llama-3-8b-instruct-v2.Q4_1.gguf	Q4_1	4.78GB
japanese-llama-3-8b-instruct-v2.Q5_0.gguf	Q5_0	5.21GB
japanese-llama-3-8b-instruct-v2.Q5_K_S.gguf	Q5_K_S	5.21GB
japanese-llama-3-8b-instruct-v2.Q5_K.gguf	Q5_K	5.34GB
japanese-llama-3-8b-instruct-v2.Q5_K_M.gguf	Q5_K_M	5.34GB
japanese-llama-3-8b-instruct-v2.Q5_1.gguf	Q5_1	5.65GB
japanese-llama-3-8b-instruct-v2.Q6_K.gguf	Q6_K	6.14GB
japanese-llama-3-8b-instruct-v2.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: llama3 language:

Japanese-LLaMA-3-8B-Instruct-v2は指示実行モデル、フルモデルです。

Meta-Llama-3-8B-Instructをベースに開発しました。