Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026
Model library → GLM-5.3-Flash → GLM-5.3-Flash 320B-A18B
320 billion parameters must all be resident — about 194 GB at Q4_K_M, so this is a multi-GPU or large-unified-memory model, not a single-card one. Only 18B activate per token, which is why it decodes at roughly the speed of a 18B dense model once loaded. Natively multimodal across text, image and video with a 1,048,576-token context. MIT licensed. Ollama publishes only a `:cloud` tag; local runners use the community GGUF conversions.
GLM-5.3-Flash 320B-A18B needs about 194 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 320 Billion (18B active) |
| Context window | 1,048,576 |
| Architecture | Hybrid-Attention MoE (multimodal) |
| Provider | Zhipu AI (Z.ai) |
| Licence | MIT |
| Specified at | Q4_K_M |
| System RAM | 256 GB |
| Record updated | 2026-09-11 |
MIT — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB), with no KV cache (this record has no published architecture). Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|
| Q2_K | 105.2 GB | 106.0 GB | — | Won't fit |
| Q3_K_M | 136.4 GB | 137.2 GB | — | Won't fit |
| Q4_K_M | 193.2 GB | 194.0 GB | — | Won't fit |
| Q5_K_M | 226.8 GB | 227.6 GB | — | Won't fit |
| Q6_K | 262.4 GB | 263.2 GB | — | Won't fit |
| Q8_0 | 340.0 GB | 340.8 GB | — | Won't fit |
| F16 | 640.0 GB | 640.8 GB | — | Won't fit |
Want the memory numbers alone, at every quantization level and your own context length? Use the GLM-5.3-Flash 320B-A18B VRAM calculator.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs GLM-5.3-Flash 320B-A18B is the Apple M3 Ultra (512 GB).
Install Ollama, then run:
ollama run glm-5.3-flash:cloudWeights on Hugging Face: zai-org/GLM-5.3-Flash.
Quality scores as published by the model's authors or an independent evaluator — not throughput, and not measured by us.
| Benchmark | Score | Provenance |
|---|---|---|
| DeepSWE | 63.4 / 100 % | vendor-claimed · https://www.marktechpost.com/2026/08/26/z-ai-releases-glm-5-3-flash-a-320b-a18b-natively-multimodal-moe-with-a-1m-token-context/ |
Best for: agentic coding, multimodal, long context, reasoning.
← All GLM-5.3-Flash models | VRAM calculator | Check your own hardware