Can Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB run GLM-5.3-Flash (320B-A18B)?
64 GB unified · 256 GB/s memory bandwidth · GLM-5.3-Flash (320B-A18B) has 320B parameters (18B active per token).
Short answer
No. It doesn't fit in memory.
Needs ≈148 GB but only ≈52 GB is available after the OS, other apps and Open WebUI.
Why it doesn’t fit
Even its smallest practical version (Q3_K_M) needs about 148 GB for the model, its context memory and the runtime. After Windows (≈7.7 GB), a browser with a few tabs (≈3.0 GB) and Open WebUI (≈1.0 GB), Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB has about 52 GB left, so it’s 96 GB short.
Ways to make it work
Close everything else
Not enough on its own: with every other app closed it’s still about 93 GB short.
Pick a smaller model from the same family
Get more memory
You’d want at least 160 GB of memory in total. The machines below are the cheapest that run it comfortably.
Check your exact setup
These pages assume typical settings. A shorter context or a lighter chat app can change the answer.
Check Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB
The same applies to every workload we rate (chat, coding questions, coding in a repository, agentic coding and long documents): they all need at least as much memory as chat.
Other models for Ryzen AI Max+ 395 mini PC / Framework Desktop · 64 GB
The best-rated models for chat on this machine.
- Qwen3.6 35B-A3B55–75 tok/sExcellent
- Gemma 4 26B-A4B45–60 tok/sExcellent
- Qwen3.5 35B-A3B55–75 tok/sExcellent
- LFM2.5 24B-A2B110–150 tok/sExcellent
- gpt-oss-20b70–90 tok/sExcellent
- GLM-4.7-Flash (30B-A3B)55–75 tok/sExcellent
Cheapest machines for GLM-5.3-Flash (320B-A18B)
Hardware rated comfortable or better for chat, lowest price first.
- Mac Studio M5 Ultra 256 GB$6,299 · 35–60 tok/sExcellent
- Mac Studio M3 Ultra 256 GB$6,299 · 25–35 tok/sExcellent
- Mac Studio M5 Ultra 512 GB$7,099 · 30–45 tok/sExcellent
- Mac Studio M3 Ultra 512 GB$7,099 · 25–35 tok/sExcellent
Same chip, other memory: 128 GB
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.