OpenModelsHQ

GLM-4.5

GLM-4.5 is an open-weight language model from Z.ai (Zhipu) with 358B parameters (mixture of experts). At 4-bit it needs about 239.9 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
239.9GB

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

Total parameters
358B
Mixture of experts, all weights counted
Context window
128K
131,072 tokens
Cheapest API, blended / 1M
$1.00
₹94 · Z.AI · 3:1 input to output
All Z.ai (Zhipu) API prices

Key information

Lab
Z.ai (Zhipu)
Released
20 Jul 2025
Parameters
358B · MoE
Type
Language
Context
131,072 tokens
License
MIT
HF downloads, 30 days
115,159
Repository
zai-org/GLM-4.5
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
GLM-4.5 needs about 239.9 GB at 4-bit, 421.2 GB at 8-bit and 791.7 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
Q4239.9 GB
Q8421.2 GB
BF16791.7 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)≈ 239.9 GBToo big 666%RubinAnnounced288 GB memory
8-bit (Q8)≈ 421.2 GBToo big 1170%No single device in our directory has enough memory
16-bit (BF16)≈ 791.7 GBToo big 2199%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.

unsloth/GLM-4.5-GGUFFind compatible hardware

Through an API

Z.AI (fp8) is the cheapest provider we found.

$0.60 / $2.20

Input / output per 1M tokens
₹57 / ₹207 at ₹94.29 per $1

Blended: $1.00 (₹94) per 1M. Ranked by a 3:1 mix of input and output tokens.

GGUF with llama.cppView repository
llama-cli -hf unsloth/GLM-4.5-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.

Hosted API 1

USD and INR per million tokensAll Z.ai (Zhipu) API prices
Precision
Z.AICheapest$1.00₹94$0.60₹57$2.20₹207131,072FP8
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does GLM-4.5 need? At an 8k context, about 239.9 GB at 4-bit, 421.2 GB at 8-bit and 791.7 GB at 16-bit (BF16). A longer context needs more.

Can I run GLM-4.5 on a Mac? No current Mac fits the 4-bit estimate of 239.9 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-4.5 supports up to 131,072 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is Z.AI, at $0.60 per 1M input tokens and $2.20 per 1M output tokens (₹57 and ₹207 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

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, OpenRouter.