Olmo 3 32B Think
Allen Institute for AI · released Nov 19, 2025 · allenai/Olmo-3-32B-Think
- Type
- Open weightsApache License 2.0
- Params
- 32.2B
- Context
- 66K
about 49K words of context
Our take
Written Aug 2, 2026Olmo 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.
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.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)111th of 143 · 1329.7
CodingWriting and fixing code on its own
Arena Coding107th of 143 · 1383.6
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
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
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.
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.
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%
GeForce RTX 4090 · 24 GB
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
GeForce RTX 5090 · 32 GB
Room to spare. 8.2 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
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.
Memory use by level
Against a 24 GB card.
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 →
Or rent it from someone else
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
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.15 / $0.50 | 66K | not measured | Unknown | Unknown | Unknown |
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
| Provider | Tool calling | JSON output | Strict 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.
When we formed this view
Dates behind this page
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.
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
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- allenai/Olmo-3-32B-Think
- Architecture
- Dense
- Modality record
- text->text
- Catalogue slug
- allenai-olmo-3-32b-think