What hardware do you need to run Gemma 4 26B-A4B?

Gemma 4 26B-A4B at Q4_K_M is 17 GB of weights, with a context ceiling of 256k tokens. 3.8B active out of 25B, so it is quick for its class. On the cheapest machine that runs it, a Framework Desktop, 32GB, it generates 41 tok/s at 32k of context, worked out from memory bandwidth.

How good is Gemma 4 26B-A4B, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 17 (reasoning mode; 13 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 Muse Glimmer 30B above it, vs Qwen3.5 122B-A10B below.

What Gemma 4 26B-A4B costs either way

Renting the same model costs $0.042 per million input tokens and $0.22 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 Gemma 4 26B-A4B

Every machine here runs it, but not to the same length. The Mac mini M6, 32GB stops at 128k; the Strix Halo Framework Desktop, 32GB takes it to 256k, which is this model's own ceiling and the longest the calculator offers. 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 256k 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 Gemma 4 26B-A4B at 256k on the Strix Halo Framework Desktop, 32GB

How much memory does Gemma 4 26B-A4B need at 256k?

Every figure above is priced at 32k of context. At 256k, which is this model's own ceiling and the longest the calculator offers, Gemma 4 26B-A4B needs 22.5 GB rather than 17.8 GB. The weights are the same either way; the key-value cache goes from 0.9 GB to 5.6 GB.

30 of the 37 machines here still sold at a published price hold Gemma 4 26B-A4B at 32k and 28 hold it at 256k. The cheapest still sold is the same at both lengths: the Framework Desktop, 32GB at $1,269.

On the Framework Desktop, 32GB it runs 41 tok/s estimated at 32k and 17 tok/s estimated at 256k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

The specifics

Parameters

25.2B, of which 3.8B are active per token

Quantisation

Q4_K_M

Weights on disk

17 GB

KV cache

0.9 GB at 32k context — 5 of 30 layers grow with the context, at two KV heads by 512 wide; the other 25 stop at a 1,024-token window. How weights and cache add up.

Maximum context

256k tokens

Licence

Apache 2.0

Sources

google/gemma-4-26B-A4B-it, unsloth/gemma-4-26b-a4b-it-GGUF