Models › Devstral Small 2 24B (2512) › Apple M4 (32 GB)
Can I run Devstral Small 2 24B (2512) on Apple M4 (32 GB)?
Yes
Yes. Devstral Small 2 24B (2512) fits fully on the Apple M4 (32 GB) at Q5_K_M (about 19.9 GB of 21 GB usable, 8k context). ESTIMATE
Verdict by quantization (8k context, f16 KV, 32 GB RAM for offload)
| Quant | Needs | Apple M4 (32 GB) (32 GB, ~21 GB GPU-usable) |
|---|---|---|
| Q3_K_M | 14.5 GB | ✅ Fits |
| IQ4_XS | 15.3 GB | ✅ Fits |
| Q4_K_M | 17.2 GB | ✅ Fits |
| MXFP4 | 16.5 GB | ✅ Fits |
| Q5_K_M | 19.9 GB | ⚠️ Fits, tight |
| Q6_K | 22.6 GB | ❌ Doesn't fit |
| Q8_0 | 28.7 GB | ❌ Doesn't fit |
| F16 | 52.4 GB | ❌ Doesn't fit |
Speed ESTIMATE
About 6 tok/s generation at Q4_K_M, scaled from measured Llama 2 7B Q4_0 runs on this chip. Not measured for Devstral Small 2 24B (2512); submit a benchmark.
Memory figures are estimates from the model's parameter count and config.json (Hugging Face). How we calculate. Last verified with data from 2026-10-22.
FAQ
Can I run Devstral Small 2 24B (2512) on the Apple M4 (32 GB)?
Yes. Devstral Small 2 24B (2512) fits fully on the Apple M4 (32 GB) at Q5_K_M (about 19.9 GB of 21 GB usable, 8k context).
How much VRAM does Devstral Small 2 24B (2512) need?
About 17.2 GB at Q4_K_M and 28.7 GB at Q8_0 with 8k context (estimate).
Other models on Apple M4 (32 GB): Qwen3.6 27B · Qwen3 Coder 30B A3B (MoE) · GLM 4.7 Flash
See all models for a 32GB Mac · all Mac sizes.
Won't fit? Free hosted options: FreeAISwap.
Will It Run? Pro NOT BUILT YET
A personal setup for your exact hardware (Ollama / llama.cpp configs ready for your coding agent), an alert when a new model fits, and a one-click cloud fallback when it doesn't.
Not built yet. Join the waitlist, $10/mo planned, no charge now. What's planned
Email only. No payment info.