OpenModelsHQ

GLM-4.7-Flash

GLM-4.7-Flash is an open-weight language model from Z.ai (Zhipu) with 31.2B parameters (mixture of experts). At 4-bit it needs about 24.1 GB of memory, so the smallest current device that fits it is the Radeon AI PRO R9700.

Overview

Estimated memory at 4-bit
24.1GB

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

Total parameters
31.2B
Mixture of experts, all weights counted
Context window
198K
202,752 tokens
Cheapest API, blended / 1M
$0.1454
₹14 · Cloudflare · 3:1 input to output
All Z.ai (Zhipu) API prices

Key information

Lab
Z.ai (Zhipu)
Released
19 Jan 2026
Parameters
31.2B · MoE
Type
Language
Context
202,752 tokens
License
MIT
HF downloads, 30 days
1,092,889
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
GLM-4.7-Flash needs about 24.1 GB at 4-bit, 39.9 GB at 8-bit and 72.1 GB at 16-bit. At 4-bit it fits GeForce RTX 5090, DGX Spark, Mac Studio M5 Ultra (256GB). 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
Q424.1 GB
Q839.9 GB
BF1672.1 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)≈ 24.1 GBFits 67%Radeon AI PRO R970032 GB memory
8-bit (Q8)≈ 39.9 GBToo big 111%L40S48 GB memory
16-bit (BF16)≈ 72.1 GBToo big 200%RTX PRO 6000 Blackwell96 GB 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.

lmstudio-community/GLM-4.7-Flash-MLX-8bitCheck your Mac

With GGUF

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

unsloth/GLM-4.7-Flash-GGUFFind compatible hardware

Through an API

Cloudflare is the cheapest provider we found.

$0.0605 / $0.40

Input / output per 1M tokens
₹5.70 / ₹38 at ₹94.29 per $1

Blended: $0.1454 (₹14) per 1M. Ranked by a 3:1 mix of input and output tokens.

MLX on Apple SiliconView repository
mlx_lm.generate --model lmstudio-community/GLM-4.7-Flash-MLX-8bit \
  --prompt "Explain how a transformer works."
GGUF with llama.cppView repository
llama-cli -hf unsloth/GLM-4.7-Flash-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 2

USD and INR per million tokensAll Z.ai (Zhipu) API prices
Precision
CloudflareCheapest$0.1454₹14$0.0605₹5.70$0.40₹38131,072Not listed
Novita$0.1525₹14$0.07₹6.60$0.40₹38200,000BF16
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-4.7-Flash need? At an 8k context, about 24.1 GB at 4-bit, 39.9 GB at 8-bit and 72.1 GB at 16-bit (BF16). A longer context needs more.

Can I run GLM-4.7-Flash on a Mac? The smallest current Mac that fits the 4-bit estimate of 24.1 GB is the Mac mini M5 Pro (48GB). An MLX build is available: lmstudio-community/GLM-4.7-Flash-MLX-8bit.

Does the full context fit? GLM-4.7-Flash 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 Cloudflare, at $0.06 per 1M input tokens and $0.40 per 1M output tokens (₹5.70 and ₹38 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