01What it can do
- MoE 320B/18B active: multimodal flagship
- Permissive MIT license
- 128k native context
- Multimodal chat / code / vision
- —Multi-GPU server class (~186 GB VRAM Q4)
- —Gated weights on Hugging Face (acceptance required)
- —Moderate throughput given the total size
04Install
Install Ollama for your OS. Check the model and its quantization before downloading. Start with 4096 tokens of context, then check placement with ollama ps. A command below is not proof that a test was run on your machine.
02Required memory
Approximate GPU VRAM required to run this model, including 4k tokens of context overhead. For a longer context, add ~1 GB per 8k-token increment.
What hardware do you need for GLM 5.3 Flash 320B-A18B?
To run GLM 5.3 Flash 320B-A18B locally with Q4 quantization, you need about 186 GB of VRAM. An option to compare: BOSGAME M5 128GB / 2TB (Ryzen AI Max+ 395) — this model exceeds this mini-PC's GPU capacity: choose a smaller model or suitable infrastructure.
Why this choice? Our complete guide on BOSGAME M5 128GB / 2TB (Ryzen AI Max+ 395) →
Affiliate links — commission possible at no extra cost to you; independent recommendations. As an Amazon Associate, BestLLMfor earns from qualifying purchases.
03Expected speed
Tokens generated per second in Q4_K_M, 4k context. Beyond 20 t/s, reading is comfortable. Below 10 t/s, that's just for testing.