What hardware do you need to run GLM-4.7-Flash?

GLM-4.7-Flash at Q4_K_M is 18 GB of weights, with a context ceiling of 198k tokens. Replaces GLM-4.5-Air at a quarter of the size and a higher score. On the cheapest machine that runs it, a Framework Desktop, 32GB, it generates 40 tok/s at 32k of context, worked out from memory bandwidth.

How good is GLM-4.7-Flash, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 15 (reasoning mode; 11 without), which puts it in the Haiku-class band. In the same band as Anthropic's cheap, fast tier. Every current OpenAI model scores above this band. See the whole table.

Head to head with its neighbours on the leaderboard: vs Granite 4.2 30B above it, vs Gemma 4 12B below. One more model needs much the same memory at 32k of context: vs Devstral Small 2 24B.

What GLM-4.7-Flash costs either way

Renting the same model costs $0.0605 per million input tokens and $0.4 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-4.7-Flash

Every machine here runs it, but not to the same length. The Mac mini M6, 32GB stops at 32k; the AMD Radeon AI PRO R9700, 32GB takes it to 128k, the longest setting below this model's own 198k limit. 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: 44 of the 56 machines on this site hold it at 32k. Within a family only memory decides, so that is every Mac Studio and Strix Halo box at any size, every NVIDIA card with 24GB or more, every Mac mini and MacBook Pro with 32GB or more, the Radeon AI PRO R9700, 32GB 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 198k 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. 2 of the 7 above reach it, and the slowest is 13 tok/s.

The cheapest machine that runs it is sold with 32 GB. There is a page on what 32 GB runs, machine by machine: it names the 6 machines here sold at that size, and the 32 current models the roomiest of them holds at 32k, this one among them.

It fits in less memory than that: the smallest size here that runs it at 32k is 24 GB, on the GeForce RTX 3090, 24GB at $1,499, card only, which hands a model 23 GB and is no longer sold.

Run GLM-4.7-Flash at 128k on the AMD Radeon AI PRO R9700, 32GB

How much memory does GLM-4.7-Flash need at 128k?

Every figure above is priced at 32k of context. At 128k, the longest setting the calculator offers below this model's own 198k limit, GLM-4.7-Flash needs 25.4 GB rather than 20.1 GB. The weights are the same either way; the key-value cache goes from 1.8 GB to 7.1 GB.

30 of the 37 machines here still sold at a published price hold GLM-4.7-Flash at 32k and 27 hold it at 128k. The cheapest still sold goes from the Framework Desktop, 32GB at $1,269 to the Radeon AI PRO R9700, 32GB at $1,299, card only. The Radeon AI PRO R9700, 32GB is priced as the card alone, so add the PC around it before comparing it with a complete computer.

On the Radeon AI PRO R9700, 32GB it runs 94 tok/s estimated at 32k and 38 tok/s estimated at 128k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

The specifics

Parameters

31.2B, of which 3B are active per token

Quantisation

Q4_K_M

Weights on disk

18 GB

KV cache

1.8 GB at 32k context — Latent attention: the cache holds one 512-wide compressed vector plus 64 RoPE dimensions per layer, 1,152 bytes a token, not the 20 KB a head count would suggest. The config states no head_dim and it cannot be derived. How weights and cache add up.

Maximum context

198k tokens

Licence

MIT

Sources

zai-org/GLM-4.7-Flash