Mistral AI
Mistral 7B Instruct v0.2
Check price at Amazon for Mistral AI Mistral-7B-Instruct-v0.2 (affiliate link, opens in new tab)Affiliate link
- Weights at 16-bit
- 14 GB
- Weights at 8-bit (Q8_0)
- 7.7 GB
- Weights at 4-bit (Q4_K_M)
- 4.4 GB
- Smallest card at 4-bit
- Intel Arc A380 · 6 GB
- Parameters
- Layers
- KV heads
- Context
- Licence
Specs
- Attention heads
- Context
- Downloads (30 days)
- GGUF downloads
-
repo bytes files quant TheBloke/Mistral-7B-Instruct-v0.2-GGUF 3,083,098,400 1 entries Q2_K TheBloke/Mistral-7B-Instruct-v0.2-GGUF 3,164,567,840 1 entries Q3_K_S TheBloke/Mistral-7B-Instruct-v0.2-GGUF 3,518,986,528 1 entries Q3_K_M TheBloke/Mistral-7B-Instruct-v0.2-GGUF 3,822,024,992 1 entries Q3_K_L TheBloke/Mistral-7B-Instruct-v0.2-GGUF 4,108,917,024 1 entries Q4_0 TheBloke/Mistral-7B-Instruct-v0.2-GGUF 4,140,374,304 1 entries Q4_K_S TheBloke/Mistral-7B-Instruct-v0.2-GGUF 4,368,439,584 1 entries Q4_K_M TheBloke/Mistral-7B-Instruct-v0.2-GGUF 4,997,716,256 1 entries Q5_0 TheBloke/Mistral-7B-Instruct-v0.2-GGUF 4,997,716,256 1 entries Q5_K_S TheBloke/Mistral-7B-Instruct-v0.2-GGUF 5,131,409,696 1 entries Q5_K_M TheBloke/Mistral-7B-Instruct-v0.2-GGUF 5,942,065,440 1 entries Q6_K TheBloke/Mistral-7B-Instruct-v0.2-GGUF 7,695,857,952 1 entries Q8_0 - Head size
- Hidden size
- KV heads
- Layers
- Licence
- Parameters
- Parameters by type
- Publisher
- Task