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. On the cheapest machine that runs it, a Framework Desktop, 128GB, it generates 10 tok/s at 32k of context, worked out from memory bandwidth.

How good is GLM-4.5-Air, 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. See the whole table.

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

Head to head with its neighbours on the leaderboard: vs Granite 4.2 8B above it, vs Mistral Small 4 (119B-2603) below. Two more models need much the same memory at 32k of context: vs Qwen3.5 122B-A10B, vs Devstral 2 123B.

Is GLM-4.5-Air still worth running?

Not on the two figures this site can compare. The intelligence index puts 19 of the current models here above GLM-4.5-Air, and not one of them asks more of a machine: at 32k of context it needs 79.2 GB and scores 11, where the strongest of the 19, Qwen3.8 27B, needs 18.6 GB and scores 34 (xhigh reasoning effort; 22 without reasoning).

The cheapest machine still sold that holds GLM-4.5-Air at 32k is the Framework Desktop, 128GB at $3,449, which holds Qwen3.8 27B as well. This site quotes Qwen3.8 27B at 10 tok/s estimated there and GLM-4.5-Air at 10 tok/s estimated. Qwen3.8 27B itself runs on the Framework Desktop, 32GB at $1,269, $2,180 less.

GLM-4.5-Air's score is Artificial Analysis's own estimate rather than a measured run of the full v4.3 suite.

What GLM-4.5-Air 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 2026-10-29). 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. What a million tokens costs each way puts the two prices side by side.

Machines that run GLM-4.5-Air

Every machine here runs it, but not to the same length. The Strix Halo Framework Desktop, 128GB stops at 64k; the DGX Spark GB10 Grace Blackwell, 128GB takes it to 128k, this model's own ceiling. The weights are the same size on every machine; what differs is the memory left for the key-value cache, which grows with every token you keep.

The table is the cheapest machine in each family, not the only one that runs it: 17 of the 56 machines on this site hold it at 32k. Within a family only memory decides, so that is every NVIDIA card with 96GB or more, every Mac Studio, Strix Halo box and MacBook Pro with 128GB or more and the DGX Spark, 128GB. One table sets every machine against the others: price, the memory its GPU can use, what it holds and how long it takes to pay for itself.

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 longest context is the longest setting the calculator offers that the machine still holds this model at, cache included, and no machine is shown taking it past its own 128k limit. Each one opens the calculator on that machine at that length.

For scale, the calculator starts from 80 tok/s for a hosted API and times a local machine against it. Nothing above reaches it, and the quickest is 39 tok/s.

The cheapest machine that runs it is sold with 128 GB. There is a page on what 128 GB runs, machine by machine: it names the 11 machines here sold at that size, and the 39 current models the roomiest of them holds at 32k.

It fits in less memory than that: the smallest size here that runs it at 32k is 96 GB, on the RTX PRO 6000 Blackwell, 96GB at $18,000, card only, which hands a model 95 GB.

Run GLM-4.5-Air at 128k on the DGX Spark GB10 Grace Blackwell, 128GB

How much memory does GLM-4.5-Air need at 128k?

Every figure above is priced at 32k of context. At 128k, this model's own ceiling, GLM-4.5-Air needs 97.7 GB rather than 79.2 GB. The weights are the same either way; the key-value cache goes from 6.2 GB to 24.7 GB.

12 of the 37 machines here still sold at a published price hold GLM-4.5-Air at 32k and two hold it at 128k. The cheapest still sold goes from the Framework Desktop, 128GB at $3,449 to the DGX Spark, 128GB at $4,699.

On the DGX Spark, 128GB it runs 13 tok/s measured at 32k and 5.5 tok/s measured at 128k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

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. How weights and cache add up.

Maximum context

128k tokens

Licence

MIT

Sources

unsloth/GLM-4.5-Air-GGUF, zai-org/GLM-4.5-Air