Written by Jakub Rusinowski · Last updated January 15, 2025
Yes
Yes — InternLM 3 8B Instruct at Q8_0 needs about 10.6 GB of the 12 GB usable on MacBook Air (M4, 16 GB) (~1.4 GB spare), at ~6.7 tok/s (estimated), with room for about 32,768 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~6.7 tok/s
| Usable memory for models | 12 GB |
| Memory bandwidth | 120 GB/s |
| Form factor | Laptop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
| Quant | Memory needed | Fits 12 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 18.8 GB | ✗ No | — | — | 17.6 GB |
| Q8_0 | 10.6 GB | ✓ Yes | 32K | ~6.7 tok/s | 9.4 GB |
| Q6_K | 8.4 GB | ✓ Yes | 32K | ~8.6 tok/s | 7.2 GB |
| Q5_K_M | 7.4 GB | ✓ Yes | 32K | ~9.9 tok/s | 6.2 GB |
| Q4_K_M | 6.5 GB | ✓ Yes | 32K | ~11.5 tok/s | 5.3 GB |
| Q3_K_M | 5 GB | ✓ Yes | 32K | ~15.9 tok/s | 3.8 GB |
| Q2_K | 4.1 GB | ✓ Yes | 32K | ~20 tok/s | 2.9 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| InternLM 3 20B Instruct | 14.5 GB | ✗ Too large | — |
| InternLM 3 8B Instruct | 6.5 GB | ✓ Fits | ~11.5 tok/s |
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Yes — InternLM 3 8B Instruct at Q8_0 needs about 10.6 GB of the 12 GB usable on MacBook Air (M4, 16 GB) (~1.4 GB spare), at ~6.7 tok/s (estimated), with room for about 32,768 tokens of context.
Q8_0 — it needs about 10.6 GB of the 12 GB available, downloads as roughly 9.4 GB, and runs at an estimated 6.7 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? | InternLM 3 model page | Check your hardware