GLM-5.3-Flash — local AI model by Zhipu AI (Z.ai)
Written by Jakub Rusinowski · Last updated
The first natively multimodal model in the GLM-5 series, and the one Z.ai actually released under MIT — 320B total parameters with 18B active, text plus image and video in, a 1M-token context, and hybrid attention (linear attention for local dependencies, sparse attention for distant retrieval). Z.ai claims 63.4 on DeepSWE against GLM-5.2's 46.2. Note this is NOT the GLM-5.3 flagship: that is a separate 753B model under a bespoke licence with a hyperscaler security-review clause.
Variants
The smallest GLM-5.3-Flash variant needs about 194 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| GLM-5.3-Flash 320B-A18B → 320B (18B active) | ~194 GB | 1,048,576 | cloud-hosted tag |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run GLM-5.3-Flash locally
Install Ollama, then pull the tag.
The Ollama tag `glm-5.3-flash:cloud` is cloud-hosted, so there is no local run command for this model.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: GLM-5.3-Flash 320B-A18BRecommended GPU
The cheapest catalogued GPU that runs GLM-5.3-Flash locally (min 194 GB VRAM) is the Apple M3 Ultra (512 GB).
Can I run GLM-5.3-Flash on my GPU?
- GLM-5.3-Flash on AMD Ryzen AI Max+ 395
- GLM-5.3-Flash on Apple M1 Ultra
- GLM-5.3-Flash on Apple M2 Max
- GLM-5.3-Flash on Apple M2 Ultra
- GLM-5.3-Flash on Apple M4 Max
- GLM-5.3-Flash on Apple M5 Max
- GLM-5.3-Flash on NVIDIA A100 80GB (PCIe)
- GLM-5.3-Flash on NVIDIA DGX Spark
- GLM-5.3-Flash on NVIDIA H100 80GB (PCIe)
- GLM-5.3-Flash on NVIDIA RTX PRO 6000 Blackwell
GLM-5.3-Flash — frequently asked questions
How much VRAM does GLM-5.3-Flash need?
GLM-5.3-Flash needs about 194 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: GLM-5.3-Flash 320B-A18B (194 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run GLM-5.3-Flash on an RTX 4090 (24 GB)?
GLM-5.3-Flash's smallest variant needs about 194 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for GLM-5.3-Flash?
Q4_K_M is the best balance of quality and VRAM for GLM-5.3-Flash in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run GLM-5.3-Flash with Ollama?
GLM-5.3-Flash has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.