Llama 4 Maverick 17B 128E Instruct FP8
Gated accessMeta·meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
Llama 4 Maverick 17B 128E Instruct FP8 is a language model published by Meta. The latest OpenRouter endpoint refresh was unavailable, so no current serving claim is made. It accepts text, image input and returns text. The published context limit is 1.0M tokens.
OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.
Providers
Uptime measured over the last 30 minutesCurrent provider status is unavailable.
Hugging Face Inference Providers
Exact repository identityProvider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.
Reported evaluation leads (1)
Excluded from scoreStructured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.
ModelCap Index · Current board
Methodology- Public rank basis
- Measured (measured)
- Index support
- 1.4% · weak
- Index interval
- 21.8–41.6
- Rank posterior
- Not available
- Top 5 / Top 10 probability
- Not available / Not available
- Posterior as of
- Snapshot timestamp unavailable
- Identity binding
- Exact catalogue product · meta-llama/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8@94125d2bd83076b21eed33119525e29eaf3894f4 (not the evaluation revision)
- Direct benchmark observations
- 1
- Breadth-adjusted BES point estimate
- 31.7
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
- Observed capability
- 51.1
- Evidence status
- provisional · 3% mass
- General preference
- —
- Coding
- —
- Agents & tools
- 51.1
- Reasoning
- —
- Evidence breadth
- 5%
- Evidence coverage
- 1%
- Usage (OpenRouter popularity)
- —
- Liquidity (providers × uptime)
- —
- Open reach (HF downloads)
- —
- Surface (context / tools / modalities)
- 55.0
- Freshness
- 15.3
- · Catalogue: context 1048576, modalities Text/Image
- · First seen 2025-04-01
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
- BFCL V4 · Function calling51.1
The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.
Deployment readiness
Metadata index- Artifact reproducibility
- 100.0
- Access & legal clarity
- 68.3
- Deployability
- 48.7
- Evaluation provenance
- 34.9
Missing: accessLegalClarity.resolvable-license-terms, deployability.measured-provider-uptime, evaluationProvenance.evaluation-dataset-revisions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market activity
Venue coverage- Market Gravity
- 8.3
- OpenRouter weekly popularity
- Not listed
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
Arena preference
This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.
Market Gravity breakdown
- Usage55%
- 0.0
- Liquidity25%
- 0.0
- Open reach15%
- 50.0
- Freshness5%
- 15.3
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
Specification
- Context window
- 1.0M tokens
- Max output
- —
- Inputs
- Text, Image
- Outputs
- Text
- Tokenizer
- —
- Cached input tokens
- Not offered
- First seen on OpenRouter
- 1 Apr 2025
Capabilities
- Not supported: Reasoning
- Not supported: Tool use
- Not supported: Structured output
- Not supported: Response format
- Not supported: Moderated
Weights & access
Gated access. The weights are hosted behind an access request or acceptance step. Review the publisher's access requirements and license before use or redistribution.
- Access
- Gated access
- Licence
- llama4
- Pinned revision
- 94125d2bd830
- Parameters
- 401.6B
- Architecture
- Llama4ForConditionalGeneration
- Model type
- llama4
- Hugging Face downloads (30d)
- 112K
- Downloads (all time)
- 1.6M
- Likes
- 174
- Repository updated
- 22 May 2025, 23:46 UTC