Check my GPU

LLMs ·

GLM-5.3 Flash (320B-A18B)

Parameters
321B (18.0B active)
Architecture
Mixture of experts
Max context
1,024K tokens
License
mit
Released
2026-08

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/GLM-5.3-Flash-GGUF (opens in a new tab)

ollama run hf.co/unsloth/GLM-5.3-Flash-GGUF

Original weights · Hugging Face

Full-precision files from Zhipu AI, for fine-tuning, vLLM, Transformers.

huggingface.co/zai-org/GLM-5.3-Flash (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Zhipu AI. The weights themselves download from Hugging Face.

github.com/zai-org/GLM-5 (opens in a new tab)

git clone https://github.com/zai-org/GLM-5

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: hybrid: 11 of 45 layers keep a (latent) KV cache; the rest use linear attention.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 129 GB 129 GB 129 GB GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
Q3_K_M Low 157 GB 158 GB 158 GB GGUF (UD-Q3_K_XL) · folder (opens in a new tab)
Q4_K_M Good 196 GB 197 GB 197 GB GGUF (UD-Q4_K_XL) · folder (opens in a new tab)
Q5_K_M High 228 GB 229 GB 229 GB GGUF (UD-Q5_K_XL) · folder (opens in a new tab)
Q6_K High 263 GB 264 GB 264 GB GGUF (UD-Q6_K_XL) · folder (opens in a new tab)
Q8_0 Very high 341 GB 341 GB 342 GB GGUF · folder (opens in a new tab)
F16 Full 643 GB 643 GB 644 GB GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for GLM-5.3 Flash (320B-A18B)

Grade · points Hardware Quant Memory Speed Fit
91 ptsExcellent (S) · 91 of 100 points: Model quality 40.8/45, Memory fit 25.0/25, Speed 11.6/15, Memory use 13.7/15 Apple M3 Ultra (512 GB) Q4_K_M 227 GB / 384 GB 24.0 tok/s Runs well
88 ptsExcellent (S) · 88 of 100 points: Model quality 36.1/45, Memory fit 24.0/25, Speed 13.2/15, Memory use 15.0/15 Apple M3 Ultra (256 GB) Q3_K_M 173 GB / 192 GB 31.1 tok/s Tight fit
83 ptsGreat (A) · 83 of 100 points: Model quality 30.1/45, Memory fit 24.0/25, Speed 14.7/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q2_K 141 GB / 144 GB 38.6 tok/s Tight fit

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.