OpenModelsHQ

GLM-4.6

GLM-4.6 is an open-weight language model from Z.ai (Zhipu) with 357B parameters (mixture of experts). At 4-bit it needs about 238.9 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
238.9GB

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

Total parameters
357B
Mixture of experts, all weights counted
Context window
198K
202,752 tokens
Cheapest API, blended / 1M
$0.70
₹66 · DeepInfra · 3:1 input to output
All Z.ai (Zhipu) API prices

Key information

Lab
Z.ai (Zhipu)
Released
29 Sep 2025
Parameters
357B · MoE
Type
Language
Context
202,752 tokens
License
MIT
HF downloads, 30 days
27,684
Repository
zai-org/GLM-4.6
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
GLM-4.6 needs about 238.9 GB at 4-bit, 419.4 GB at 8-bit and 788.3 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
Q4238.9 GB
Q8419.4 GB
BF16788.3 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)≈ 238.9 GBToo big 664%RubinAnnounced288 GB memory
8-bit (Q8)≈ 419.4 GBToo big 1165%No single device in our directory has enough memory
16-bit (BF16)≈ 788.3 GBToo big 2190%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

Start with the MLX files, built for Apple Silicon.

mlx-community/GLM-4.6-4bitCheck your Mac

With GGUF

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

unsloth/GLM-4.6-GGUFFind compatible hardware

Through an API

DeepInfra (fp4) is the cheapest provider we found.

$0.40 / $1.60

Input / output per 1M tokens
₹38 / ₹151 at ₹94.29 per $1

Blended: $0.70 (₹66) per 1M. Ranked by a 3:1 mix of input and output tokens.

MLX on Apple SiliconView repository
mlx_lm.generate --model mlx-community/GLM-4.6-4bit \
  --prompt "Explain how a transformer works."
GGUF with llama.cppView repository
llama-cli -hf unsloth/GLM-4.6-GGUF \
  -c 8192 -p "Explain how a transformer works."

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

Hosted API 4

USD and INR per million tokensAll Z.ai (Zhipu) API prices
Precision
DeepInfraCheapest$0.70₹66$0.40₹38$1.60₹151202,752FP4
Venice$0.76₹72$0.43₹41$1.75₹165198,000FP4
Novita$0.9625₹91$0.55₹52$2.20₹207204,800BF16
Z.AI$1.00₹94$0.60₹57$2.20₹207202,752FP4
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-4.6 need? At an 8k context, about 238.9 GB at 4-bit, 419.4 GB at 8-bit and 788.3 GB at 16-bit (BF16). A longer context needs more.

Can I run GLM-4.6 on a Mac? No current Mac fits the 4-bit estimate of 238.9 GB. The smallest Mac in our directory that does is the Mac Studio M3 Ultra (512GB), which is discontinued. An MLX build is available: mlx-community/GLM-4.6-4bit.

Does the full context fit? GLM-4.6 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 DeepInfra, at $0.40 per 1M input tokens and $1.60 per 1M output tokens (₹38 and ₹151 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