Can I Run Qwen3.8 on Mac Studio (M2 Ultra, 192 GB)?
Written by Jakub Rusinowski · Last updated September 11, 2026
Yes
Yes — Qwen3.8-Flash-Next at Q5_K_M needs about 128.6 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB) (~15.4 GB spare), at ~77.4 tok/s (estimated), with room for about 262,144 tokens of context.
Confidence: high · Recommended quantization: Q5_K_M · Estimated speed: ~77.4 tok/s
See what else this hardware can run →
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Mac Studio (M2 Ultra, 192 GB) — what it gives a model
| Usable memory for models | 144 GB |
| Memory bandwidth | 800 GB/s |
| Form factor | Desktop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
Qwen3.8 on Mac Studio (M2 Ultra, 192 GB): memory by quantization
| Quant | Memory needed | Fits 144 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 361 GB | ✗ No | — | — | 360 GB |
| Q8_0 | 192.3 GB | ✗ No | — | — | 191.3 GB |
| Q6_K | 148.6 GB | ✗ No | — | — | 147.6 GB |
| Q5_K_M | 128.6 GB | ✓ Yes | 256K | ~77.4 tok/s | 127.6 GB |
| Q4_K_M | 109.7 GB | ✓ Yes | 256K | ~87 tok/s | 108.7 GB |
| Q3_K_M | 77.7 GB | ✓ Yes | 256K | ~110.3 tok/s | 76.7 GB |
| Q2_K | 60.2 GB | ✓ Yes | 256K | ~129.4 tok/s | 59.2 GB |
Which Qwen3.8 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| Qwen3.8-Max | 1457.5 GB | ✗ Too large | — |
| Qwen3.8-Flash-Next | 109.7 GB | ✓ Fits | ~87 tok/s |
| Qwen3.8 27B | 18.3 GB | ✓ Fits | ~23.7 tok/s |
What to watch out for
- 1 larger variant of Qwen3.8 does not fit and would need CPU offload or different hardware.
- Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.
Mac Studio M2 Ultra 192 GB limitations
- Superseded by the M3 Ultra, which is why it is often the better used buy for large-model work.
- Memory is soldered; the configuration chosen at purchase is permanent.
Recommended setup
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 192 GB unified memory at 800 GB/s, shared between CPU and GPU.
- macOS reserves a share of unified memory for the system, so not all of it is available to a model.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run Qwen3.8 on Mac Studio (M2 Ultra, 192 GB)?
Yes — Qwen3.8-Flash-Next at Q5_K_M needs about 128.6 GB of the 144 GB usable on Mac Studio (M2 Ultra, 192 GB) (~15.4 GB spare), at ~77.4 tok/s (estimated), with room for about 262,144 tokens of context.
Which quantization of Qwen3.8 should I use on Mac Studio (M2 Ultra, 192 GB)?
Q5_K_M — it needs about 128.6 GB of the 144 GB available, downloads as roughly 127.6 GB, and runs at an estimated 77.4 tokens/sec with up to 256K of context.
What limits Qwen3.8 on Mac Studio (M2 Ultra, 192 GB)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Other Computers
Other Models on Mac Studio (M2 Ultra, 192 GB)
- Qwen3-Coder on Mac Studio (M2 Ultra, 192 GB)
- SmolLM2 on Mac Studio (M2 Ultra, 192 GB)
- SmolLM3 on Mac Studio (M2 Ultra, 192 GB)
- StarCoder 2 on Mac Studio (M2 Ultra, 192 GB)
- Aya 3B (Tiny Aya) on Mac Studio (M2 Ultra, 192 GB)
Qwen3.8 on GPUs
- Qwen3.8 on NVIDIA GeForce RTX 5090
- Qwen3.8 on NVIDIA GeForce RTX 5080
- Qwen3.8 on NVIDIA GeForce RTX 5070 Ti
- Qwen3.8 on NVIDIA GeForce RTX 5070