Skip to content
Mistral AI

Mistral 7B Instruct v0.2

Maker’s page
Check price at Amazon for Mistral AI Mistral-7B-Instruct-v0.2 (affiliate link, opens in new tab)
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
repobytesfilesquant
TheBloke/Mistral-7B-Instruct-v0.2-GGUF3,083,098,4001 entriesQ2_K
TheBloke/Mistral-7B-Instruct-v0.2-GGUF3,164,567,8401 entriesQ3_K_S
TheBloke/Mistral-7B-Instruct-v0.2-GGUF3,518,986,5281 entriesQ3_K_M
TheBloke/Mistral-7B-Instruct-v0.2-GGUF3,822,024,9921 entriesQ3_K_L
TheBloke/Mistral-7B-Instruct-v0.2-GGUF4,108,917,0241 entriesQ4_0
TheBloke/Mistral-7B-Instruct-v0.2-GGUF4,140,374,3041 entriesQ4_K_S
TheBloke/Mistral-7B-Instruct-v0.2-GGUF4,368,439,5841 entriesQ4_K_M
TheBloke/Mistral-7B-Instruct-v0.2-GGUF4,997,716,2561 entriesQ5_0
TheBloke/Mistral-7B-Instruct-v0.2-GGUF4,997,716,2561 entriesQ5_K_S
TheBloke/Mistral-7B-Instruct-v0.2-GGUF5,131,409,6961 entriesQ5_K_M
TheBloke/Mistral-7B-Instruct-v0.2-GGUF5,942,065,4401 entriesQ6_K
TheBloke/Mistral-7B-Instruct-v0.2-GGUF7,695,857,9521 entriesQ8_0
Head size
Hidden size
KV heads
Layers
Licence
Parameters
Parameters by type
Publisher
Task

More from Mistral AI