Mistral AI
Mistral 7B Instruct v0.3
Check price at Amazon for Mistral AI Mistral 7B Instruct v0.3 (affiliate link, opens in new tab)Affiliate link
- Weights at 16-bit
- 15 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)
- Family
- GGUF downloads
-
repo bytes files quant lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF 3,288,846,560 1 entries IQ3_M lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF 3,825,979,616 1 entries Q3_K_L lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF 4,130,066,656 1 entries IQ4_NL lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF 4,372,812,000 1 entries Q4_K_M lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF 5,136,175,328 1 entries Q5_K_M lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF 5,947,248,864 1 entries Q6_K lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF 7,702,565,088 1 entries Q8_0 lmstudio-community/Mistral-7B-Instruct-v0.3-GGUF 28,992,851,904 1 entries F32 - Head size
- Hidden size
- KV heads
- Layers
- Licence
- Parameters
- Parameters by type
- Publisher
More from Mistral AI
Across the range 4 models by family
Mistral 7BMistral AI Mistral 7B Instruct v0.3 · 32,768 tokens