Models / Allen Institute for AI/ Olmo 3 32B Think

Olmo 3 32B Think

Allen Institute for AI · released Nov 19, 2025 · allenai/Olmo-3-32B-Think

Input: text. Output: text.InputOutput
Type
Open weightsApache License 2.0
Params
32.2B
Context
66K

about 49K words of context

Our take

Written Aug 2, 2026

Olmo 3 is a thirty-two-billion-parameter text model from the Allen Institute for AI, released in late 2025 with a permissive Apache licence. It has broad leaderboard coverage across six task types, with coding as its strongest suit and creative writing as its weakest.

Who should pick it

Pick this for open-weights research and fine-tuning where a permissive licence matters, or for coding tasks where it scores highest among its own skills. Use it when you are comfortable with a single provider and its pricing. Skip it if you need price competition between hosts, if creative writing quality is critical, or if you want measured throughput data before choosing.

The case for it

  • Broad, recent leaderboard coverage with consistent scores across six task types, evaluated in July 2026.
  • Permissive Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
  • Coding performance leads its own skill profile, with a gap of more than ninety points above its creative writing score.

The case against it

  • Only one tracked offer, giving no price competition between providers.
  • Creative writing lags its other capabilities by a wide margin.
  • No active-parameter count disclosed, so efficiency claims are unverified in our data.
00

How good is it?

IntelligencePuzzles, maths, exam questions

1.5 of 5

Arena Text (overall)111th of 143 · 1329.7

Arena Hard Prompts 108th of 143Arena Maths 108th of 139

CodingWriting and fixing code on its own

2 of 5

Arena Coding107th of 143 · 1383.6

Arena Coding is the only board that has scored it for this.

AgenticPlanning, calling tools, staying on task

not measured

Nobody we watch has scored Olmo 3 32B Think for this. We would take the rating from Arena Agent (IPS).

WritingWe do not rate this

Scored, not ratedThe placings are on the right.

Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Olmo 3 32B Think placed and give it no mark out of five.

Arena Creative Writing 112th of 143 · 1291.1
Also scored, on boards we give no mark for
Arena Instruction Following 108th of 143

These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.

Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
1383.6independentsource ↗
1349.4independentsource ↗
1311.4independentsource ↗
1329.7independentsource ↗
01

Can you run it yourself?

Fits in memory
weights load entirely on the card
Spills to system RAM
some weights offload; much slower
Too large
will not load even with offload
est
size is calculated; the verdict could change by 10%
A card many people ownFits in memoryest

GeForce RTX 4090 · 24 GB

Weights at Q4_K_M20.3 / 24 GBest
Spare memory0.2 GB spare
Usable context2K of 66K
Decode speed41 tok/sest

Borderline fit on an estimated size. It leaves 0.2 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.

Comfortable fit

One step upFits in memory

GeForce RTX 5090 · 32 GB

Weights at Q4_K_M20.3 / 32 GBest
Spare memory8.2 GB spare
Usable context33K of 66K
Decode speed73 tok/sest

Room to spare. 8.2 GB spare means a 10% error in the size would not change the answer.

On a MacFits in memoryest

Apple M1 Pro (16-core GPU) · 32 GB

Weights at Q4_K_M20.3 / 32 GBest
Spare memory1.4 GB spare
Usable context4K of 66K
Decode speed7 tok/sest

Borderline fit on an estimated size. It leaves 1.4 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.

Your hardware
Checking your profile…

Memory use by level

Against a 24 GB card.

Q4_K_M
recommended
20.3 GBest
Fits in memoryest
Q5_K_M
23.8 GBest
Spills to system RAM
Q8_0
35.6 GBest
Too large

All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.

Check against your own machine → · All 71 devices, with every size →

02

Or rent it from someone else

Cheapest published offer

Cheapest of 1 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.

per 1M tokens
$0.15 in / $0.50 out
Context served
66K
Throughput
Not measured
Current provider offers with price, context and prompt-privacy answers
ProviderIn / out per 1M tokensContextThroughputTrains on promptsLogs promptsZero retention
OpenRouter$0.15 / $0.5066Knot measuredUnknownUnknownUnknown

Across the 1 listings we hold: 0 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.

What each host's API supports

From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.

Supported
Not supported
Not published
host gave no parameter list
API features per host
ProviderTool callingJSON outputStrict schema
OpenRouter

Tool calling: 0 of 1 listings say yes, 1 says no. JSON output: 1 of 1 listings says yes. Strict schema: 1 of 1 listings says yes.

03

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 1383.6 on Arena Codingleaderboard
Aug 2, 2026BenchmarkScored 1291.1 on Arena Creative Writingleaderboard
Aug 2, 2026BenchmarkScored 1349.4 on Arena Hard Promptsleaderboard
Aug 2, 2026BenchmarkScored 1321.8 on Arena Instruction Followingleaderboard
Aug 2, 2026BenchmarkScored 1311.4 on Arena Mathsleaderboard
Aug 2, 2026BenchmarkScored 1329.7 on Arena Text (overall)leaderboard
Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Nov 19, 2025AnnouncedOlmo 3 32B Think announced by Allen Institute for AI

Prices last checked 14h ago

What we do not know about this model yet

  • We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
  • 1 of 1 listings do not say whether they train on prompts.
  • We hold no cached-input rate for any of its listings.
04

Licence and identifiers

What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.

Licence

Apache License 2.0

permissiveCommercial use allowed

Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.

Identifiers

Architecture
Dense
Modality record
text->text
Catalogue slug
allenai-olmo-3-32b-think

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us