Can Laptop · Core Ultra 7 258V (Arc 140V) · 32 GB run GLM-5.3-Flash (320B-A18B)?
32 GB unified · 136 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 ≈24 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 (≈4.5 GB), a browser with a few tabs (≈3.0 GB) and Open WebUI (≈1.0 GB), Laptop · Core Ultra 7 258V (Arc 140V) · 32 GB has about 24 GB left, so it’s 125 GB short.
Ways to make it work
Close everything else
Not enough on its own: with every other app closed it’s still about 122 GB short.
Pick a smaller model from the same family
Get more memory
You’d want at least 157 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 Laptop · Core Ultra 7 258V (Arc 140V) · 32 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 Laptop · Core Ultra 7 258V (Arc 140V) · 32 GB
The best-rated models for chat on this machine.
- LFM2.5 24B-A2B30–50 tok/sExcellent
- gpt-oss-20b18–30 tok/sExcellent
- Gemma 4 26B-A4B15–25 tok/sExcellent
- Qwen3.6 35B-A3B25–45 tok/sExcellent
- Qwen3.5 35B-A3B25–45 tok/sExcellent
- MiniCPM5 2B19–30 tok/sExcellent
Cheapest machines for GLM-5.3-Flash (320B-A18B)
Hardware rated comfortable or better for chat, lowest price first.
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.