Skip to content

Meta · Chat

Llama 3.2 90B Vision Instruct

Meta 🇺🇸ChatLlama familyOpen weights. One of its sources says the weights are publicly available.
From Requesty's listing:
A lightweight and ultra-fast variant of Llama 3.3 70B, for use when quick response times are needed most.
llminfo IQ
106.1
Market median price
$0.90 blended / 1M
Max context
131K
Listings
11

Evidence and sources

🤗 meta-llama/Llama-3.2-90B-Vision-Instructllminfo IQ 106.1, ranked among chat models. From 54 benchmarks. Plenty of data behind it.How llminfo IQ is computedGood value (57.0). Cheaper per task than its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 19 Sep 2024Maker HQ: US (according to Meta's own website)
Sources: LMArena data, Models.dev data, Requesty data, Hugging FacePrimary data from LMArena from Models.dev: weights availability from Requesty: description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 7 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 4 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionFunction calling

Listings

 Aihubmixmeta-llama/Llama-3.2-90B-Vision-InstructSource: AIHubMix data docsNot published by the provider$0.50$0.50
 OpenRouterllama-3.2-90b-vision-instructSource: GenAI Prices dataNot published by the provider$1.20$1.20
 RequestyInference by DeepInfradeepinfra/meta-llama/Llama-3.2-90B-Vision-InstructSource: Requesty data131K$0.35$0.40
 Fireworks AIfireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instructSource: LiteLLM data131K$0.90$0.90
 Ionetmeta-llama/Llama-3.2-90B-Vision-InstructSource: Models.dev data16K$0.35cache read $0.175$0.40cache write $0.70
 Ocioci/meta.llama-3.2-90b-vision-instructSource: LiteLLM data128K$2.00$2.00
 Watsonxwatsonx/meta-llama/llama-3-2-90b-vision-instructSource: LiteLLM data128K$2.00$2.00

4 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Math

U-MATH7 related benchmarks · 21 results
algebra accuracy
Source: U-MATH and mu-MATH
Task set · algebra · gpt-4o-2024-08-06
differential_calc accuracy
Source: U-MATH and mu-MATH
Task set · differential_calc · gpt-4o-2024-08-06
integral_calc accuracy
Source: U-MATH and mu-MATH
Task set · integral_calc · gpt-4o-2024-08-06
multivariable_calculus accuracy
Source: U-MATH and mu-MATH
Task set · multivariable_calculus · gpt-4o-2024-08-06
overall accuracy
Source: U-MATH and mu-MATH
Task set · u_math · gpt-4o-2024-08-06
precalculus_review accuracy
Source: U-MATH and mu-MATH
Task set · precalculus_review · gpt-4o-2024-08-06
Show 3 more resultsHide 3 results
sequences_series accuracy
Source: U-MATH and mu-MATH
Task set · sequences_series · gpt-4o-2024-08-06

Vision

Agentic

Human preference

Science

Reasoning

General

Knowledge

OCR

Other

Data credits: OpenVLM Leaderboard (OpenCompass / VLMEvalKit), Apache-2.0 (licence) · LMArena, CC BY 4.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Toloka, U-MATH and mu-MATH public leaderboard. MIT Space; generated solution outputs retain underlying model terms and are not ingested. (licence)

Around the web

Also known as: deepinfra/meta-llama/llama-3.2-90b-vision-instruct, fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct, meta-llama/llama-3.2-90b-vision-instruct, meta/llama-3.2-90b-vision-instruct, nim/meta/llama-3.2-90b-vision-instruct, nvidia_nim/meta/llama-3.2-90b-vision-instruct, oci/meta.llama-3.2-90b-vision-instruct, vertex_ai/meta/llama-3.2-90b-vision-instruct-maas, watsonx/meta-llama/llama-3-2-90b-vision-instruct

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works