Can Mac Pro M2 Ultra 192 GB run GLM-4.7-Flash (30B-A3B)?
192 GB unified · 800 GB/s memory bandwidth · GLM-4.7-Flash (30B-A3B) has 31.2B 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 (24 GB of weights) on LM Studio. Generation: 95–130 tok/s, leaving about 157 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 | 95–130 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Excellent | 6-bit | 90–120 tok/s | ≈2 s | 16K | Details |
| Coding in a repositorywith Aider | Comfortable | 6-bit | 75–100 tok/s | ≈6 s | 32K | Details |
| Agentic codingwith OpenCode | Comfortable | 6-bit | 70–90 tok/s | ≈9 s | 32K | Details |
| Long documents (64K)with Open WebUI | Excellent | 6-bit | 45–65 tok/s | ≈30 s | 64K | Details |
Speeds are estimates calibrated against measured benchmarks on similar hardware. “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/GLM-4.7-Flash-GGUF:Q6_K
Downloads 24.69 GB (Q6_K). Ollama's default context is small: set OLLAMA_CONTEXT_LENGTH=65536 before `ollama serve` for long prompts.
Other models for Mac Pro M2 Ultra 192 GB
The best-rated models for chat on this machine.
- gpt-oss-120b85–120 tok/sExcellent
- Qwen3.6 35B-A3B100–130 tok/sExcellent
- Qwen3-Next 80B-A3B Instruct100–130 tok/sExcellent
- Gemma 4 26B-A4B80–110 tok/sExcellent
- Qwen3.5 35B-A3B100–130 tok/sExcellent
- LFM2.5 24B-A2B190–260 tok/sExcellent
Cheapest machines for GLM-4.7-Flash (30B-A3B)
Hardware rated comfortable or better for chat, lowest price first.
- Laptop · Ryzen AI 9 HX 370 (Radeon 890M) · 32 GB$1,300 · 25–40 tok/sComfortable
- Laptop · Core Ultra 7 258V (Arc 140V) · 32 GB$1,300 · 20–35 tok/sComfortable
- Mac mini M4 32 GB$1,399 · 30–40 tok/sExcellent
- Desktop PC · Ryzen 9 9950X (no GPU) · 64 GB DDR5$1,400 · 10–17 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
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.