What hardware do you need to run GLM-4.5-Air?

GLM-4.5-Air at Q4_K_M is 73 GB of weights, with a context ceiling of 128k tokens. Built for agentic coding; unusually good tool use for a model this size. Needs 96 GB or more.

Cheapest machine that runs itStrix Halo Framework Desktop, 128GB at $3,449

Fastest of the ones listedMac Studio M5 Ultra, 256GB — 26 tok/s at 32k context

Honest answer on costPays back in 139 years at 500k tokens a day.

How good is it, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 11, which puts it in the Below every hosted tier band. Fine for simple, well-specified tasks. Noticeably less capable than anything the big labs sell today. Score source. See the whole table.

Summarising — good
Translation — good
Everyday coding — good
Reasoning & maths — usable
Agentic work — good

What it costs either way

Renting the same model costs $0.13 per million input tokens and $0.85 per million output (OpenRouter, cheapest active endpoint, checked 2026-09-03). Buying a machine only beats that if you use it hard enough, for long enough, that the hardware price divides down below the rental bill.

Machines that run it

Machine	Price	Speed at 32k	Pay-back
Strix Halo Framework Desktop, 128GB	$3,449	10 tok/s estimated	Pays back in 139 years	Run the numbers
DGX Spark GB10 Grace Blackwell, 128GB	$4,699	13 tok/s measured	Pays back in 184 years	Run the numbers
Mac Studio M5 Max, 128GB	$5,099	13 tok/s estimated	Pays back in 196 years	Run the numbers
MacBook Pro M5 Max (16-inch), 128GB	$6,999	13 tok/s estimated	Pays back in 269 years	Run the numbers

One machine per family, cheapest first. Speeds are measured where a public benchmark exists and estimated from memory bandwidth otherwise; the calculator says which for any configuration.

The specifics

Parameters: 110.5B, of which 12B are active per token
Quantisation: Q4_K_M
Weights on disk: 73 GB
KV cache: 6.2 GB at 32k context
Maximum context: 128k tokens (128k)
Licence: MIT
Sources: source 1, source 2