OpenModelsHQ

GLM-5

GLM-5 is an open-weight language model from Z.ai (Zhipu) with 754B parameters (mixture of experts). At 4-bit it needs about 509.1 GB of memory, more than any single device in our directory has.

Overview

Estimated memory at 4-bit
509.1GB

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

Total parameters
754B
Mixture of experts, all weights counted
Context window
198K
202,752 tokens
Cheapest API, blended / 1M
$0.93
₹88 · GMICloud · 3:1 input to output
All Z.ai (Zhipu) API prices

Key information

Lab
Z.ai (Zhipu)
Released
11 Feb 2026
Parameters
754B · MoE
Type
Language
Context
202,752 tokens
License
MIT
HF downloads, 30 days
1,240,185
Repository
zai-org/GLM-5
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
GLM-5 needs about 509.1 GB at 4-bit, 890.5 GB at 8-bit and 1670 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
Q4509.1 GB
Q8890.5 GB
BF161670 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)≈ 509.1 GBToo big 1414%No single device in our directory has enough memory
8-bit (Q8)≈ 890.5 GBToo big 2474%No single device in our directory has enough memory
16-bit (BF16)≈ 1670 GBToo big 4639%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

No trusted GGUF build found yet.

Find compatible hardware

Through an API

GMICloud (fp8) is the cheapest provider we found.

$0.60 / $1.92

Input / output per 1M tokens
₹57 / ₹181 at ₹94.29 per $1

Blended: $0.93 (₹88) per 1M. Ranked by a 3:1 mix of input and output tokens. Tied with StreamLake.

Hosted API 9

USD and INR per million tokensAll Z.ai (Zhipu) API prices
Precision
GMICloudCheapest$0.93₹88$0.60₹57$1.92₹181202,752FP8
StreamLake$0.93₹88$0.60₹57$1.92₹181198,000FP8
Baidu$1.085₹102$0.70₹66$2.24₹211202,752FP8
SiliconFlow$1.35₹127$0.95₹90$2.55₹240204,800FP8
Amazon Bedrock$1.55₹146$1.00₹94$3.20₹302202,752Not listed
Novita$1.55₹146$1.00₹94$3.20₹302202,800FP8
Venice$1.55₹146$1.00₹94$3.20₹302198,000FP8
Z.AI$1.55₹146$1.00₹94$3.20₹302202,752FP8
Venice$1.90₹179$1.20₹113$4.00₹377200,000Not listed
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-5 need? At an 8k context, about 509.1 GB at 4-bit, 890.5 GB at 8-bit and 1670 GB at 16-bit (BF16). A longer context needs more.

Can I run GLM-5 on a Mac? No Mac in our directory has enough usable memory for the 4-bit estimate of 509.1 GB. We have not found a trusted MLX or GGUF build yet.

Does the full context fit? GLM-5 supports up to 202,752 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 GMICloud, at $0.60 per 1M input tokens and $1.92 per 1M output tokens (₹57 and ₹181 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens. Tied with StreamLake.

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, OpenRouter.