Meta
Llama 3 8B Instruct
Check price at Amazon for Meta Meta-Llama-3-8B-Instruct (affiliate link, opens in new tab)Affiliate link
- Weights at 16-bit
- 16 GB
- Weights at 8-bit (Q8_0)
- 8.5 GB
- Weights at 4-bit (Q4_K_M)
- 4.9 GB
- Smallest card at 4-bit
- Intel Arc A380 · 6 GB
Specs
- Downloads (30 days)
- GGUF downloads
-
repo bytes files quant lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF 3,784,822,976 1 entries IQ3_M lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF 4,920,733,888 1 entries Q4_K_M lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF 5,732,987,072 1 entries Q5_K_M lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF 6,596,006,080 1 entries Q6_K lmstudio-community/Meta-Llama-3-8B-Instruct-GGUF 8,540,770,496 1 entries Q8_0 - Licence
- Parameters
- Parameters by type
- Publisher
- Task