Mac › 24 GB
Best local LLMs for a 24GB Mac
Short answer: A 24GB Mac lets the GPU use about 16 GB by default (~67%). That fits Raon-1 mini preview 28.8B A4.3B (MoE) at Q3_K_M with room for 8k context. Best picks: Raon-1 mini preview 28.8B A4.3B (MoE), Qwen3.8 27B, Qwen3.6 27B. Memory figures are estimates. Speeds are measured llama.cpp results where we have them and labeled estimates otherwise.
Checked 2026-10-22 · memory figures are estimates; measured speeds link their source
| Model | Quant | Memory needed (estimated, 8k ctx) | Fits default limit | Speed on Apple M4 Pro (24 GB) | Format |
|---|---|---|---|---|---|
| Raon-1 mini preview 28.8B A4.3B (MoE) MoE | Q3_K_M | 15.8 GB | Y | not measured | GGUF |
| Qwen3.8 27B | Q3_K_M | 15.7 GB | Y | ~14 tok/s est. | GGUF |
| Qwen3.6 27B | Q3_K_M | 15.7 GB | Y | ~14 tok/s est. | GGUF |
| Qwen3.5 27B | Q3_K_M | 15.7 GB | Y | ~14 tok/s est. | GGUF |
| Gemma 4 26B A4B (MoE) MoE | IQ4_XS | 15.5 GB | Y | not measured | GGUF |
| Devstral Small 2 24B (2512) | IQ4_XS | 15.3 GB | Y | ~15 tok/s est. | GGUF |
| LFM2.5 24B A2B (MoE) MoE | Q4_K_M | 16.0 GB | Y | not measured | GGUF |
| gpt-oss 20B (MoE) MoE | Q4_K_M | 14.1 GB | Y | not measured | GGUF |
| Phi 4 reasoning vision 15B | Q6_K | 15.3 GB | Y | ~15 tok/s est. | GGUF |
| Ministral 3 14B (2512) | Q6_K | 13.9 GB | Y | ~16 tok/s est. | GGUF |
| Gemma 4 12B | Q8_0 | 14.8 GB | Y | ~15 tok/s est. | GGUF |
| GLM 4.6V Flash | Q8_0 | 12.4 GB | Y | ~17 tok/s est. | GGUF |
| Qwen3.5 9B | Q8_0 | 11.6 GB | Y | ~18 tok/s est. | GGUF |
| Ministral 3 8B (2512) | Q8_0 | 11.7 GB | Y | ~20 tok/s est. | GGUF |
| granite 4.2 8b | Q8_0 | 11.8 GB | Y | ~20 tok/s est. | GGUF |
| Qwen3 VL 8B | Q8_0 | 11.6 GB | Y | ~20 tok/s est. | GGUF |
| LFM2.5 8B A1B (MoE) MoE | Q8_0 | 10.1 GB | Y | not measured | GGUF |
| Gemma 4 E4B | Q8_0 | 9.7 GB | Y | ~22 tok/s est. | GGUF |
| Gemma 4 E2B | Q8_0 | 6.4 GB | Y | ~35 tok/s est. | GGUF |
| Qwen3.5 4B | Q8_0 | 6.1 GB | Y | ~38 tok/s est. | GGUF |
| Qwen3 4B (2507) | Q8_0 | 6.3 GB | Y | ~44 tok/s est. | GGUF |
| Nemotron Labs Dory 1.0 4B | Q8_0 | 5.5 GB | Y | ~45 tok/s est. | GGUF |
| NVIDIA Nemotron 3 Nano 4B | Q8_0 | 5.2 GB | Y | ~45 tok/s est. | GGUF |
| Ministral 3 3B (2512) | Q8_0 | 5.8 GB | Y | ~46–47 tok/s est. | GGUF |
| Qwen3.5 2B | Q8_0 | 3.2 GB | Y | ~78–80 tok/s est. | GGUF |
Best quant = highest of Q8_0, Q6_K, Q5_K_M, Q4_K_M, IQ4_XS, Q3_K_M that fits the default limit, f16 KV cache, 8k context. Speeds are llama.cpp (GGUF) figures; we don't have MLX runs. Estimated speeds are scaled from measured Llama 2 7B runs on the same chip and are not done for MoE models.
Why your Mac shows less than 24 GB
macOS caps how much unified memory the GPU can wire. We assume about 67% (about 16 GB here), roughly 67% below 64 GB and 75% at 64 GB and up. You can raise the cap with sudo sysctl iogpu.wired_limit_mb=…, at your own risk; leave room for macOS and your apps. These shares are approximate. Method.
Which Macs have 24GB
Apple M2 (24 GB), Apple M3 (24 GB), Apple M4 (24 GB), Apple M4 Pro (24 GB), Apple M5 (24 GB), Apple M5 Pro (24 GB).
FAQ
Is 24GB enough to run an LLM on a Mac?
Yes. 25 of 64 current models in our list fit fully at Q3_K_M or better with 8k context, the largest being Raon-1 mini preview 28.8B A4.3B (MoE) at Q3_K_M (about 15.8 GB, estimate). Bigger models need a Mac with more memory.
How much of my Mac's memory can the GPU use?
By default macOS caps GPU wired memory at roughly 67% of total below 64 GB and roughly 75% at 64 GB and up, so about 16 GB on a 24GB Mac (approximate). The iogpu.wired_limit_mb sysctl can raise it, at your own risk.
Is MLX faster than llama.cpp on a Mac?
We haven't measured it. Public tests conflict: MLX often shows higher generation tok/s, but one M1 Max test found GGUF in llama.cpp finished short-output tasks faster because of prompt processing. See our MLX vs GGUF answer for the sources.
Can a 24GB Mac run a 70B model?
No, not at the default limit. Llama 3.3 70B Instruct needs about 48.2 GB at Q4_K_M with 8k context (estimate), more than the roughly 16 GB the GPU can use.
Mac or a used RTX 3090 for local LLMs?
It's a trade. The 3090 has 24 GB of VRAM and is usually faster on models that fit. A 24GB Mac gives the GPU about 16 GB, so it fits less than a 3090. Check both in the checker.
Other Mac tiers: 16 GB Mac · 32 GB Mac · all Mac sizes · GPUs: 16 GB VRAM · What to buy
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.
Get the weekly "new models & what it takes to run them" email
Free. One email a week. Unsubscribe anytime.