Skip to content
Mistral AI

Mixtral 8x7B Instruct v0.1

Maker’s page
Check price at Amazon for Mistral AI Mixtral 8x7B Instruct v0.1 (affiliate link, opens in new tab)
Weights at 16-bit
93 GB
Weights at 8-bit (Q8_0)
50 GB
Weights at 4-bit (Q4_K_M)
28 GB
Smallest card at 4-bit
GeForce RTX 5090 · 32 GB
Parameters
Active parameters
Layers
KV heads
Context
Licence

Specs

Active parameters
Attention heads
Context
Downloads (30 days)
Experts
Experts per token
Family
GGUF downloads
repobytesfilesquant
TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF15,644,035,0081 entriesQ2_K
TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF20,363,356,0961 entriesQ3_K_M
TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF26,441,533,3761 entriesQ4_0
TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF26,441,533,3761 entriesQ4_K_M
TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF32,229,279,6801 entriesQ5_0
TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF32,229,279,6801 entriesQ5_K_M
TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF38,378,760,1281 entriesQ6_K
TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF49,624,262,5921 entriesQ8_0
Head size
Hidden size
KV heads
Layers
Licence
Parameters
Parameters by type
Publisher
Released

More from Mistral AI

Across the range 4 models by family