Can Mac Studio M5 Ultra 256 GB run Qwen3.5 35B-A3B?
256 GB unified · 1228 GB/s memory bandwidth · Qwen3.5 35B-A3B has 36B parameters (3B active per token).
Short answer
Yes, excellent for chat and comfortable or better for every workload we test.
Best quantization for chat: 6-bit (28 GB of weights) on LM Studio. Generation: 140–240 tok/s, leaving about 217 GB free for your other apps.
How it rates for each workload
Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.
| Workload | Verdict | Quant | Generation | First reply | Context | |
|---|---|---|---|---|---|---|
| Chatwith Open WebUI | Excellent | 6-bit | 140–240 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Excellent | 6-bit | 140–230 tok/s | under 1 s | 16K | Details |
| Coding in a repositorywith Aider | Comfortable | 6-bit | 130–210 tok/s | ≈1 s | 32K | Details |
| Agentic codingwith OpenCode | Comfortable | 6-bit | 120–200 tok/s | ≈2 s | 32K | Details |
| Long documents (64K)with Open WebUI | Excellent | 6-bit | 100–170 tok/s | ≈5 s | 64K | Details |
Speeds are bandwidth-based estimates; no direct benchmark exists for this pair. “First reply” is the time to read the workload’s opening prompt. How we calculate
Get it running
Copy-paste commands for the 6-bit build with a 64K context. Ollama and llama.cpp download the file straight from Hugging Face.
ollama run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF:Q6_K
Downloads 28.85 GB (Q6_K). Ollama's default context is small: set OLLAMA_CONTEXT_LENGTH=65536 before `ollama serve` for long prompts.
Other models for Mac Studio M5 Ultra 256 GB
The best-rated models for chat on this machine.
- gpt-oss-120b120–210 tok/sExcellent
- Qwen3.6 35B-A3B140–240 tok/sExcellent
- Qwen3-Next 80B-A3B Instruct140–230 tok/sExcellent
- Gemma 4 26B-A4B110–190 tok/sExcellent
- LFM2.5 24B-A2B280–460 tok/sExcellent
- Qwen3.5 122B-A10B50–85 tok/sExcellent
Cheapest machines for Qwen3.5 35B-A3B
Hardware rated comfortable or better for chat, lowest price first.
- Mac mini M4 32 GB$1,399 · 30–45 tok/sExcellent
- Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5$1,400 · 11–18 tok/sComfortable
- Desktop PC · Intel Arc Pro B60 24GB · 32 GB RAM$1,500 · 70–120 tok/sExcellent
- Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB$1,600 · 55–75 tok/sExcellent
- Desktop PC · Intel Arc Pro B60 24GB · 64 GB RAM$1,628 · 70–120 tok/sExcellent
- Mac mini M2 Pro 32 GB$1,699 · 55–75 tok/sExcellent
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.