What hardware do you need to run Gemma 3 27B it?

Gemma 3 27B it at Q4_K_M is 17 GB of weights, with a context ceiling of 128k tokens. Good writer and translator. Coding is serviceable; tool use is not its thing. On the cheapest machine that runs it, a Framework Desktop, 32GB, it generates 9.8 tok/s at 32k of context, worked out from memory bandwidth.

How good is Gemma 3 27B it, really?

On the Artificial Analysis Intelligence Index v4.3 it scores 5, 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 — usable
• Reasoning & maths — usable
• Agentic work — don’t

Head to head with its neighbours on the leaderboard: vs Qwen3 8B above it, vs Ministral 3 8B below. Also head to head: vs Gemma 4 31B it, the current Gemma nearest it in size. Three more models need much the same memory at 32k of context: vs Qwen3.6 27B, vs Devstral Small 2 24B, vs Mistral Small 3.2 24B Instruct.

Is Gemma 3 27B it still worth running?

Not on the two figures this site can compare. The intelligence index puts 14 of the current models here above Gemma 3 27B it, and not one of them asks more of a machine: at 32k of context it needs 19.7 GB and scores 5, where the strongest of the 14, Qwen3.8 27B, needs 18.6 GB and scores 34 (xhigh reasoning effort; 22 without reasoning).

The cheapest machine still sold that holds Gemma 3 27B it at 32k is the Framework Desktop, 32GB at $1,269, which holds Qwen3.8 27B as well. This site quotes Qwen3.8 27B at 10 tok/s estimated there and Gemma 3 27B it at 9.8 tok/s estimated.

What Gemma 3 27B it costs either way

Renting the same model costs $0.08 per million input tokens and $0.16 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 3 27B it

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, 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: 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 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 63 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.

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 3 27B it at 128k on the AMD Radeon AI PRO R9700, 32GB

How much memory does Gemma 3 27B it need at 128k?

Every figure above is priced at 32k of context. At 128k, this model's own ceiling, Gemma 3 27B it needs 27.7 GB rather than 19.7 GB. The weights are the same either way; the key-value cache goes from 3.1 GB to 11.2 GB.

30 of the 37 machines here still sold at a published price hold Gemma 3 27B it at 32k and 26 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 28 tok/s estimated at 32k and 20 tok/s estimated at 128k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

What has been measured running Gemma 3 27B it

Every speed in the table above is worked out from memory bandwidth, and that is not because nobody has run Gemma 3 27B it. Two machines here have a published speed for it, and the table above has none of them: one is no longer sold and one is still sold but not the cheapest of its family. They are below, as published and again at 32k of context, which is what every other speed on this page is taken at.

A published figure is what its source reports, at the window the model was run at. The 32k figure is that measurement read at 32k of context: every token generated reads the weights and the whole key-value cache, so the longer the window the slower it runs. A discontinued machine's price is the one it launched at. Each published figure links the source that took it.

The specifics

Parameters

27.4B

Quantisation

Q4_K_M

Weights on disk

17 GB

KV cache

3.1 GB at 32k context — 5 of every 6 layers use a 1024-token sliding window. How weights and cache add up.

Maximum context

128k tokens (input)

Licence

Gemma Terms of Use

Sources

bartowski/google_gemma-3-27b-it-GGUF, unsloth/gemma-3-27b-it