Llama 4 Scout
Meta · released Apr 2, 2025 · meta-llama/Llama-4-Scout-17B-16E-Instruct
- Type
- Open weightsCustom licence
- Params
- 109B
- Context
- 1.3M
about 983K words of context · download allowed, licence restricts use
Our take
Written Sep 29, 2026Llama 4 Scout is a downloadable model with a very large request capacity and image input, but it sits near the bottom of the field on the dated boards we can quote, and its licence puts conditions on commercial use. Try it through a host before committing to a download.
Use it for long-document work where a report or a stack of documents need not be split up first, and where you can judge the output yourself. Its licence puts conditions on commercial use and redistribution, so it needs reading before you build on it. Skip it if you need measured coding or agentic software-engineering ability, or if you want a model near the top of the preference boards.
The case for it
- A very large request capacity, so a long report or a stack of documents goes in beside the question without being split up first.
- Text and images go into the same request, so a screenshot or a diagram does not have to be described in words first.
- Cheap to try through a host, with several listed offers well under the dearest of them.
The case against it
- 137th of 168 on Arena Text (overall) as of 25 Sep 2026, and 135th of 168 on Arena Coding as of 25 Sep 2026 — human-preference boards, so they record which answer people preferred rather than whether it was correct.
- 41st of 42 on SWE-bench Verified via mini-SWE-agent as of 19 Feb 2026, which measures the share of real GitHub issues resolved end-to-end inside that harness.
- The licence puts conditions on commercial use and redistribution (Custom licence), so a commercial product needs the terms checked first.
How good is it?
An open text model from Meta for chat and general use, though it trails most models on everyday questions, writing and coding.
- getting answers to everyday questionsArena Text (overall) · 137th of 168
- drafts, rewrites and editingArena Creative Writing · 134th of 168
- writing and completing codeArena Coding · 135th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)137th of 168 · 1322
CodingWriting and fixing code on its own
Arena Coding135th of 168 · 1363
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent. It is on SWE-bench Verified, in 41st of 42 with 9.1.
WritingDrafting and rewriting prose
Arena Creative Writing134th of 168 · 1289
Arena Creative Writing is the only board that has scored it for this.
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.
Every published score for this model7 scoresEvery figure we hold, from 7 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?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M1 Ultra (64-core GPU) · 128 GB
Room to spare. 23.9 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.10 in / $0.30 out
- Context served
- 1.3M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.10 / $0.30checked 4 hours ago | 1.3M | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8Direct and through OpenRouter | $0.10 / $0.30checked 4 hours ago | 328K16K max reply through OpenRouter | 32 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Novita AIbf16Direct and through OpenRouter | $0.18 / $0.59checked 4 hours ago | 131K118K max reply through OpenRouter | 28 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterConfirmed |
| Google Vertex AIus-east5Through OpenRouter | $0.25 / $0.70checked 4 hours ago | 1.3M8K max reply | 102 tok/s | No | No | Confirmed |
DeepInfra
Novita AI
Google Vertex AIAcross the 4 listings we hold: 3 say they do not train on prompts (2 of them only through OpenRouter), 0 say they do and 1 does not say. 3 appear in the zero-retention registry we check (2 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| DeepInfrafp8Direct and through OpenRouter | ✗ | ✗ | ✓ |
| Novita AIbf16Direct and through OpenRouter | ✗ | ✗ | ✗ |
| Google Vertex AIus-east5Through OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 2 of 4 listings say yes, 2 say no. JSON output: 2 of 4 listings say yes, 2 say no. Strict schema: 3 of 4 listings say yes, 1 says no.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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 4 listings does not say whether it trains on prompts, and 2 answer only through OpenRouter, not for their own listing.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, 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
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- meta-llama/Llama-4-Scout-17B-16E-Instruct
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- meta-llama-llama-4-scout