Mistral AI
Mistral Small 3 24B Instruct (2501)
Check price at Amazon for Mistral AI Mistral Small 3 24B Instruct (2501) (affiliate link, opens in new tab)Affiliate link
- Weights at 16-bit
- 48 GB
- Weights at 8-bit (Q8_0)
- 26 GB
- Weights at 4-bit (Q4_K_M)
- 15 GB
- Smallest card at 4-bit
- Intel Arc A770 16GB · 16 GB
- Parameters
- Layers
- KV heads
- Context
- Licence
Specs
- Attention heads
- Context
- Downloads (30 days)
- Family
- GGUF downloads
-
repo bytes files quant unsloth/Mistral-Small-24B-Instruct-2501-GGUF 8,890,325,248 1 entries Q2_K unsloth/Mistral-Small-24B-Instruct-2501-GGUF 9,047,611,648 1 entries Q2_K_L unsloth/Mistral-Small-24B-Instruct-2501-GGUF 11,474,082,048 1 entries Q3_K_M unsloth/Mistral-Small-24B-Instruct-2501-GGUF 14,333,909,248 1 entries Q4_K_M unsloth/Mistral-Small-24B-Instruct-2501-GGUF 16,763,984,128 1 entries Q5_K unsloth/Mistral-Small-24B-Instruct-2501-GGUF 19,345,938,688 1 entries Q6_K unsloth/Mistral-Small-24B-Instruct-2501-GGUF 25,054,779,648 1 entries Q8_0 unsloth/Mistral-Small-24B-Instruct-2501-GGUF 47,153,518,848 1 entries BF16 - 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
Mistral Small 3Mistral AI Mistral Small 3 24B Instruct (2501) · 24 B
Mistral Small 3Mistral AI Mistral Small 3 24B Instruct (2501) · 32,768 tokens