OpenModelsHQ

GLM-5.3-Flash-BF16

GLM-5.3-Flash-BF16 is an open-weight vision and language model from Z.ai (Zhipu) with 321B parameters (mixture of experts). At 4-bit it needs about 218.7 GB of memory, so the smallest device in our directory that fits it is the Rubin, which is announced but not shipping yet.

Overview

Estimated memory at 4-bit
218.7GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
321B
Mixture of experts, all weights counted
Context window
1024K
1,048,576 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Z.ai (Zhipu)
Released
25 Aug 2026
Parameters
321B · MoE
Type
Vision and language
Context
1,048,576 tokens
License
MIT
HF downloads, 30 days
55,207
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
GLM-5.3-Flash-BF16 needs about 218.7 GB at 4-bit, 381.3 GB at 8-bit and 713.6 GB at 16-bit. At 4-bit it fits none of the reference devices. Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q4218.7 GB
Q8381.3 GB
BF16713.6 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 218.7 GBToo big 607%RubinAnnounced288 GB memory
8-bit (Q8)≈ 381.3 GBToo big 1059%No single device in our directory has enough memory
16-bit (BF16)≈ 713.6 GBToo big 1982%No single device in our directory has enough memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

Choose a file for llama.cpp or a compatible app.

bartowski/GLM-5.3-Flash-BF16-GGUFFind compatible hardware

Through an API

No hosted API found.

GGUF with llama.cppView repository
llama-cli -hf bartowski/GLM-5.3-Flash-BF16-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of llama.cpp. We have not run them; check each repository for available files.

More about this model

Frequently asked questions

How much memory does GLM-5.3-Flash-BF16 need? At an 8k context, about 218.7 GB at 4-bit, 381.3 GB at 8-bit and 713.6 GB at 16-bit (BF16). A longer context needs more.

Can I run GLM-5.3-Flash-BF16 on a Mac? No current Mac fits the 4-bit estimate of 218.7 GB. The smallest Mac in our directory that does is the Mac Studio M3 Ultra (512GB), which is discontinued. We have not found a trusted MLX build yet, but a GGUF build is available.

Does the full context fit? GLM-5.3-Flash-BF16 supports up to 1,048,576 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

MIT. This license permits commercial use, modification and redistribution, as long as the copyright and license notice are kept. This summary is not legal advice.

Read MIT

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, GGUF repository.