Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Llama 4 Maverick 17B 128E Instruct FP8

Score basis

Llama 4 Maverick 17B 128E Instruct FP8 has too few ranked results yet to rate it on any capability.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability.

No capability has enough ranked results to rate yet.

Price

$0.27input$0.85outputper million tokens

From novita · All prices

Cheaper than 64% of 328 priced models · 3:1 input-to-output blend, log scale

Evidence

13results on13benchmarks

  • 13 independently verified

From 8 sources · latest Aug 23, 2026 · How verification works

Llama 4 Maverick 17B 128E Instruct FP8 benchmark results

13 results on 13 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Coding

Not enough dataFull coding ranking

0 of 10 ranked benchmarks measured

Instruction Following

Not enough dataFull instruction following ranking

0 of 3 ranked benchmarks measured

Factuality

Not enough dataFull factuality ranking

0 of 4 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 4 more resultsHide 4 results

Llama 4 Maverick 17B 128E Instruct FP8: common questions

Who makes Llama 4 Maverick 17B 128E Instruct FP8?

Llama 4 Maverick 17B 128E Instruct FP8 is made by Meta.

When was Llama 4 Maverick 17B 128E Instruct FP8 released?

Llama 4 Maverick 17B 128E Instruct FP8's weights were first published on Hugging Face on Apr 1, 2025.

How much does Llama 4 Maverick 17B 128E Instruct FP8 cost?

Llama 4 Maverick 17B 128E Instruct FP8 costs $0.27 per million input tokens and $0.85 per million output tokens, according to novita. At a mix of three input tokens to one output token, it is cheaper than 64% of the 328 priced models we track.

How many benchmarks has Llama 4 Maverick 17B 128E Instruct FP8 been tested on?

We track 13 results for Llama 4 Maverick 17B 128E Instruct FP8 on 13 benchmarks from 8 sources, 13 of them independently verified. The latest was recorded on Aug 23, 2026.

About this record

Where Llama 4 Maverick 17B 128E Instruct FP8's numbers come from, and every name it appears under.

Tracked since
May 2, 2026
Newest source mention
Jun 26, 2026

Where the results come from

Verification: 13 scores · 13 independently verified. How these tiers are assigned

From 8 sources on 3 sites. storage.googleapis.com supplies 6 of them; the 13 independently verified results come from 3 sites. Bars are coloured by trust tier.

  • storage.googleapis.com6
  • raw.githubusercontent.com4
  • huggingface.co3

Also known as

Llama 4 Maverick (17Bx128E) Instruct FP8llama-4-maverick-17b-128e-instruct