Sunk Cost sunkcost.ai Data checked 2026-09-03

What hardware do you need to run Olmo 3.1 32B Think?

Olmo 3.1 32B Think at Q4_K_M is 19 GB of weights, with a context ceiling of 64k tokens. The reasoning model of Ai2's Olmo 3 family, and the same weights, the same geometry and the same memory as Olmo 3.1 32B Instruct: what differs is the training after the base model and what the model does with a question. It writes its working out between <think> tags before it answers, and Ai2's own recommended settings allow 32,768 tokens for the two together, so a hard question can cost tens of thousands of generated tokens before the reply starts. That is the trade on a machine that generates every token itself. Ai2 publishes the pretraining data, the post-training datasets, the training code and the intermediate checkpoints with the weights, all under Apache 2.0. It is dense and English-only. On Ai2's own evaluation table it is level with Qwen 3 32B at maths, 96.2 against 95.4 on MATH and 78.1 against 70.9 on AIME 2025, well ahead at following awkward instructions, 68.1 against 37.3 on IFBench, and behind on general knowledge and competition coding, 86.4 against 88.8 on MMLU, 57.5 against 67.3 on GPQA and 83.3 against 90.2 on LiveCodeBench v3. Those are the publisher's figures, and nobody has placed this model on the index the rest of this site is ranked by. On the cheapest machine that runs it, a Framework Desktop, 32GB, it generates 8.6 tok/s at 32k of context, worked out from memory bandwidth.

Cheapest machine that runs itStrix Halo Framework Desktop, 32GB at $1,269
Shortest pay-backAMD Radeon AI PRO R9700, 32GB — Pays back in 90 years
Fastest machine that runs itNVIDIA RTX PRO 6000 Blackwell, 96GB at $18,000card only — 65 tok/s estimated at 32k context
Honest answer on costPays back in 101 years at 500k tokens a day.

How good is Olmo 3.1 32B Think, really?

It has not been placed on the intelligence index yet. See the whole table.

Head to head with the models that need much the same memory at 32k of context: vs Ornith 1.5 35B-A3B, vs Olmo 3.1 32B Instruct.

What Olmo 3.1 32B Think costs either way

Nobody rents Olmo 3.1 32B Think by the token. The closest hosted match, Gemma 4 31B it, costs $0.1 per million input tokens and $0.34 per million output (OpenRouter, cheapest active endpoint, checked 2026-11-15). 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 Olmo 3.1 32B Think

Every machine here runs it, but not to the same length. The Strix Halo Framework Desktop, 32GB stops at 32k; the AMD Radeon AI PRO R9700, 32GB takes it to 64k, 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.

MachinePriceSpeed at 32kLongest contextPay-back
Strix Halo Framework Desktop, 32GB $1,269 8.6 tok/s estimated 32k Pays back in 101 years Run the numbers
AMD Radeon AI PRO R9700, 32GB $1,299card only 25 tok/s estimated 64k Pays back in 90 years Run the numbers
NVIDIA GeForce RTX 5090, 32GB $1,999card only 55 tok/s estimated 64k Pays back in 130 years Run the numbers
Mac mini M5 Pro, 48GB $2,299 10 tok/s estimated 64k Pays back in 168 years Run the numbers
Mac Studio M5 Max, 36GB $2,499 15 tok/s estimated 64k Pays back in 157 years Run the numbers
MacBook Pro M5 Pro (16-inch), 48GB $3,599 10 tok/s estimated 64k Pays back in 264 years Run the numbers
DGX Spark GB10 Grace Blackwell, 128GB $4,699 9.1 tok/s estimated 64k Pays back in 387 years Run the numbers

The table is the cheapest machine in each family, not the only one that runs it: 41 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 48GB 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 64k 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 55 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 40 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 Olmo 3.1 32B Think at 64k on the AMD Radeon AI PRO R9700, 32GB

How much memory does Olmo 3.1 32B Think need at 64k?

Every figure above is priced at 32k of context. At 64k, this model's own ceiling, Olmo 3.1 32B Think needs 24.6 GB rather than 22.4 GB. The weights are the same either way; the key-value cache goes from 3 GB to 5.1 GB.

28 of the 37 machines here still sold at a published price hold Olmo 3.1 32B Think at 32k and 27 hold it at 64k. 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 25 tok/s estimated at 32k and 23 tok/s estimated at 64k. Every token generated reads the whole cache back, so a longer window is slower as well as bigger.

Two more machines, at a shorter window

The table above lists the machines that run it at 32k, the context the calculator starts on, where Olmo 3.1 32B Think needs 22 GB. Two more machines hold it at a shorter window, because the weights are the same size either way and the key-value cache is not. None of them is cheaper than the table above, which starts at $1,269.

MachinePriceLongest window it fitsNeeds there
Mac mini M6, 32GB $1,299 8k 21 GB
MacBook Pro M5 (14-inch), 32GB $2,399 8k 21 GB

One machine per family, cheapest first, from the same list as the table above. Each window is the longest setting the calculator offers that the machine still holds this model at, and it opens the calculator on that machine at that length. What it needs there is the weights plus the key-value cache at that window, measured against the memory each machine's GPU can address, which that machine's own page gives.

The specifics

Parameters
32.2B
Quantisation
Q4_K_M
Weights on disk
19 GB
KV cache
3.0 GB at 32k context — 16 of the 64 layers grow with the context; the other 48 stop at a 4,096-token window, three local layers to every global one. Both kinds cache the same geometry, eight KV heads by 128 wide, so a token costs 4,096 bytes in whichever layer holds it. How weights and cache add up.
Maximum context
64k tokens (which the config reaches by scaling the positions of a model pretrained at 8,192 tokens)
Licence
Apache 2.0
Sources
allenai/Olmo-3.1-32B-Think, allenai/Olmo-3.1-32B-Think (config), bartowski/allenai_Olmo-3.1-32B-Think-GGUF, openrouter.ai