GLM-5.3 — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
753B parameters in a 256-expert MoE (8 routed per token, about 40B active) with multi-head latent attention and DeepSeek-style sparse attention; 1M-token context. Every expert must be resident, so at Q4_K_M it needs a multi-GPU server. Z.ai serves it with SGLang and vLLM; Ollama lists only a cloud-hosted tag.
GLM-5.3 needs about 456 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.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 249.2 GB | — | Too big | |
| Q3_K_M 3.41 bpw | 322.6 GB | — | Too big | |
| Q4_K_M 4.83 bpw | 456.3 GB | — | Too big | |
| Q5_K_M 5.67 bpw | 535.4 GB | — | Too big | |
| Q6_K 6.56 bpw | 619.2 GB | — | Too big | |
| Q8_0 8.50 bpw | 801.9 GB | — | Too big | |
| F16 16.00 bpw | 1508.1 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. GLM-5.3 VRAM calculator →
Get GLM-5.3 running
GLM-5.3 is not practical on a single consumer GPU: it needs about 455.6 GB at Q4_K_M, more than any single device in our catalogue holds with headroom. How multi-GPU inference works, or rent a multi-GPU server by the hour:
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.
How to run GLM-5.3
No local Ollama tag. Ollama lists glm-5.3 only as a cloud-hosted ':cloud' tag, which runs on Ollama's servers, not your machine.
Specifications
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed. Still unconfirmed: active parameters.
- Parameters
- 753 Billion (40B active)
- Context window
- 1,048,576
- Architecture
- Sparse MoE (256 experts, 8 active), MLA + sparse attention
- Provider
- Zhipu AI (Z.ai)
- Licence
- GLM-5.3 License (MIT-style, with a security-review clause for large Model-as-a-Service operators)
- Availability
- Weights downloadable
- Practical deployment
- Multi-GPU server
- Specified at
- Q4_K_M
- System RAM
- 512 GB
- Record updated
- 2026-10-13
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
See also GLM-5.3-Flash 320B-A18B
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Independent evaluation — not vendor-claimed and not measured by us
| Benchmark | Score | Provenance |
|---|---|---|
| AA Intelligence Index v4.3.2 (Max) | 45 | independent · Artificial Analysis · snapshot 2026-10-13 |
GLM-5.3 — frequently asked questions
How much VRAM does GLM-5.3 need?
About 456 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does GLM-5.3 run on an RTX 4090 (24 GB)?
No. GLM-5.3 needs about 456 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.
How do I run GLM-5.3 locally?
No local Ollama tag. Ollama lists glm-5.3 only as a cloud-hosted ':cloud' tag, which runs on Ollama's servers, not your machine. Running the published tag would send your prompts to a hosted GPU rather than your own machine.