Written by Jakub Rusinowski · Last updated February 10, 2026
Yes
Yes — EXAONE 3.5 32B at Q8_0 needs about 36.9 GB of the 48 GB usable on Mac Studio (M4 Max, 64 GB) (~11.1 GB spare), at ~8.3 tok/s (estimated), with room for about 32,768 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~8.3 tok/s
| Usable memory for models | 48 GB |
| Memory bandwidth | 546 GB/s |
| Form factor | Desktop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 48 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 66.9 GB | ✗ No | — | — | 64 GB |
| Q8_0 | 36.9 GB | ✓ Yes | 32K | ~8.3 tok/s | 34 GB |
| Q6_K | 29.2 GB | ✓ Yes | 32K | ~10.6 tok/s | 26.2 GB |
| Q5_K_M | 25.6 GB | ✓ Yes | 32K | ~12.1 tok/s | 22.7 GB |
| Q4_K_M | 22.3 GB | ✓ Yes | 32K | ~14.1 tok/s | 19.3 GB |
| Q3_K_M | 16.6 GB | ✓ Yes | 32K | ~19.2 tok/s | 13.6 GB |
| Q2_K | 13.5 GB | ✓ Yes | 32K | ~24 tok/s | 10.5 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| EXAONE 3.5 32B | 22.3 GB | ✓ Fits | ~14.1 tok/s |
| EXAONE 3.5 7.8B | 6.6 GB | ✓ Fits | ~48.7 tok/s |
| EXAONE 3.5 2.4B | 2.9 GB | ✓ Fits | ~112.4 tok/s |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes — EXAONE 3.5 32B at Q8_0 needs about 36.9 GB of the 48 GB usable on Mac Studio (M4 Max, 64 GB) (~11.1 GB spare), at ~8.3 tok/s (estimated), with room for about 32,768 tokens of context.
Q8_0 — it needs about 36.9 GB of the 48 GB available, downloads as roughly 34 GB, and runs at an estimated 8.3 tokens/sec with up to 32K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
← Can I Run It? | EXAONE 3.5 model page | Check your hardware