MistralMistral Small 24B Instruct on NVIDIA GeForce RTX 4070 Ti Super
RTX 4070 Ti Super runs Mistral Small 24B Instruct at Q3_K_M — 18 tok/s. Usable on 16 GB VRAM — see full quantization options below.
Model Size
24B
Device VRAM
16 GB
Bandwidth
672 GB/s
Quantization
Q3_K_M
Performance by Quantization
OwnRig currently has one published compatibility entry for Mistral Small 24B Instruct on NVIDIA GeForce RTX 4070 Ti Super at Q3_K_M. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| Q3_K_M | 18 tok/s | 500ms | ✓ Yes | Acceptable | estimated |
Notes
Q3_K_M
Q3 required for 16GB. Usable with quality compromise.
About Mistral Small 24B Instruct
Mistral Small 24B Instruct (24B) is a chat, coding, reasoning model. Mistral's efficient 24B model with chat, coding, and reasoning capabilities.
View all Mistral Small 24B Instruct hardware options →About NVIDIA GeForce RTX 4070 Ti Super
NVIDIA GeForce RTX 4070 Ti Super has 16 GB at 672 GB/s. Street price: $779.
See all models NVIDIA GeForce RTX 4070 Ti Super can run →Estimate method: Community benchmarks and estimated performance. Reference hardware source: github.com (2026-03-01)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.