Llama 3.2 3B Instruct
Meta · released Sep 18, 2024 · meta-llama/Llama-3.2-3B-Instruct
- Type
- Open weightsLlama 3.2 Community License
- Params
- 3.2B
- Context
- 131K
about 98K words of context · download allowed, licence restricts use
Our take
Written Aug 3, 2026Llama 3.2 is a tiny text-only model from Meta that can handle up to 131,072 tokens in a single request — an unusually long reach for something this small. It is built for edge devices and cost-sensitive workloads where context length matters more than raw knowledge.
Pick this for simple instruction tasks that need very long context at minimal cost, or for edge deployment where a lightweight download must still read large documents. It is the practical choice when you want to stay inside a tight inference budget. Skip it if you need deep subject knowledge, strong reasoning, or a permissive licence — the community licence carries usage limits for large deployers, and its academic scores are weak.
The case for it
- Exceptionally long request limit for its size: 131,072 tokens at only 3.2 billion parameters.
- Among the cheapest hosted inference we track in its class.
- Instruction-following score of 72% is a clear bright spot against otherwise modest benchmark results.
The case against it
- Weak on knowledge and reasoning tests: 20.2% on MMLU-Pro and 2.8% on GPQA Diamond.
- Arena scores are tightly clustered across all six categories we track, with no standout domain from coding to creative writing.
- Llama 3.2 Community Licence is not fully permissive; large deployers face usage restrictions.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)142nd of 143 · 1166.4
CodingWriting and fixing code on its own
Arena Coding142nd of 143 · 1176
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Llama 3.2 3B Instruct 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 Llama 3.2 3B Instruct 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 model9 scoresEvery figure we hold, from 9 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%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 19.5 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 27.5 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 2.7 GB spare means a 10% error in the size would not 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 4 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
- $0.050 in / $0.33 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Novita AI | $0.030 / $0.050 | 33K | not measured | Unknown | Unknown | Unknown |
| OpenRouter | $0.050 / $0.33 | 131K | not measured | Unknown | Unknown | Unknown |
| Parasailbf16 | $0.050 / $0.33 | 131K | 61 tok/s | No | No | Confirmed |
| Cloudflare Workers AI | $0.051 / $0.34 | 80K | 73 tok/s | No | Yesunknown period | Unknown |
Novita AI
Cloudflare Workers AIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 1 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 |
|---|---|---|---|
| Novita AI | |||
| OpenRouter | ✗ | ✗ | ✓ |
| Parasailbf16 | ✗ | ✗ | ✓ |
| Cloudflare Workers AI | ✗ | ✗ | ✗ |
Tool calling: 0 of 4 listings say yes, 3 say no, 1 publishes no parameter list. JSON output: 0 of 4 listings say yes, 3 say no, 1 publishes no parameter list. Strict schema: 2 of 4 listings say yes, 1 says no, 1 publishes no parameter list.
Models people weigh against Llama 3.2 3B Instruct
When we formed this view
Dates behind this page
Prices last checked 38h 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.
- 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 4 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 allowsLlama 3.2 Community License, 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
Llama 3.2 Community License
Same terms as Llama 3.1 (700M MAU cap, naming rules). The multimodal 3.2 models add a clause restricting use by entities domiciled in the EU.
Identifiers
- Hugging Face
- meta-llama/Llama-3.2-3B-Instruct
- Modality record
- text->text
- Catalogue slug
- meta-llama-llama-3-2-3b-instruct