ZMIME
Comparison · 2 models · Updated Nov 2, 2026

Llama-3.2-90B-Vision-Instruct vs Gemma 3 4B IT

Llama-3.2-90B-Vision-Instruct comes out ahead, 44 to 36 on our weighted score.

  1. Our pick

    Meta

    Llama-3.2-90B-Vision-Instruct

    Released Sep 25, 2024

    44/100
    • ECI125.5
    • Price—
    • Context128K
    Full specs Remove Llama-3.2-90B-Vision-Instruct

  2. Google

    Gemma 3 4B IT

    Released Mar 12, 2025

    36/100
    • ECI115.8
    • Price$0.05 / $0.10
    • Context131K
    Full specs Remove Gemma 3 4B IT

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Llama-3.2-90B-Vision-Instruct is our pick

Llama-3.2-90B-Vision-Instruct is the better all-round choice, scoring 44/100 against Gemma 3 4B IT (36). It leads on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityLlama-3.2-90B-Vision-InstructCapabilities Index (ECI): Llama-3.2-90B-Vision-Instruct 125.5 · Gemma 3 4B IT 115.8
  • Lowest priceGemma 3 4B ITGemma 3 4B IT $0.063 per 1M tokens (3:1 blend) · Llama-3.2-90B-Vision-Instruct unpriced
  • Longest contextGemma 3 4B ITGemma 3 4B IT 131,072 · Llama-3.2-90B-Vision-Instruct 128,000 tokens
  • Widest inputsSame inputsLlama-3.2-90B-Vision-Instruct: Text, Images · Gemma 3 4B IT: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightLlama-3.2-90B-Vision-InstructGemma 3 4B IT
CapabilityCapabilities Index (ECI)67%4634
Inputs & features20%5050
Context window13%2425
Overall100%44/10036/100

Left out because at least one model lacks the data: price. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Llama-3.2-90B-Vision-Instruct vs Gemma 3 4B IT specifications side by side
SpecificationLlama-3.2-90B-Vision-InstructMetaGemma 3 4B ITGoogle
Capability
Capabilities Index (ECI)125.5 (best)115.8
ECI rank#150 of 165 (best)#163 of 165
GPQA DiamondGraduate-level science questions41.0% (best)23.2%
OTIS Mock AIME 2024–2025Competition mathematics2.6%7.5% (best)
Price per million tokens
Input—$0.05
Output—$0.10
Cached input——
Blended (3:1)—$0.063
Long-context rate—Same rate
Price source—Median of 9 providers
Limits
Context window128,000 tokens131,072 tokens (best)
Max output4,096 tokens131,072 tokens (best)
Inputs and features
TextYesYes
ImagesYesYes
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningNoNo
Tool callingYesYes
Structured outputNoNo
Availability
WeightsOpenLlama 3.2 Community LicenseOpen
API model ID——
API providers110 (best)
ReleasedSep 25, 2024Mar 12, 2025
Knowledge cutoffDec 2023Aug 2024
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Llama-3.2-90B-Vision-Instruct—
  • Gemma 3 4B IT$0.70
04 — Questions

Which should you choose?

Which is better: Llama-3.2-90B-Vision-Instruct or Gemma 3 4B IT?

Llama-3.2-90B-Vision-Instruct is the better all-round choice, scoring 44/100 against Gemma 3 4B IT (36). It leads on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, Llama-3.2-90B-Vision-Instruct or Gemma 3 4B IT?

Gemma 3 4B IT is cheaper at $0.05 input / $0.10 output per million tokens (median across 9 API providers). . At a typical mix of three input tokens to one output token, that is $0.063 per million tokens for Gemma 3 4B IT versus . Llama-3.2-90B-Vision-Instruct has no published per-token price.

Which scores higher on benchmarks?

Llama-3.2-90B-Vision-Instruct scores higher on the Capabilities Index (ECI): Llama-3.2-90B-Vision-Instruct 125.5 (#150 of 165) and Gemma 3 4B IT 115.8 (#163 of 165). The confidence ranges of the top two overlap (120.3–127.4 vs 97.9–123.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — Llama-3.2-90B-Vision-Instruct 41.0%, Gemma 3 4B IT 23.2%; OTIS Mock AIME 2024–2025 — Gemma 3 4B IT 7.5%, Llama-3.2-90B-Vision-Instruct 2.6%.

Which is better for coding?

There are no published SWE-bench Verified results for Llama-3.2-90B-Vision-Instruct and Gemma 3 4B IT yet, so there is no like-for-like coding score. On overall capability, Llama-3.2-90B-Vision-Instruct leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

Gemma 3 4B IT has the largest context window at 131,072 tokens, against 128,000 for Llama-3.2-90B-Vision-Instruct. Maximum output per response: Llama-3.2-90B-Vision-Instruct up to 4,096, Gemma 3 4B IT up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Llama-3.2-90B-Vision-Instruct accepts text and images; Gemma 3 4B IT accepts text and images. They handle the same number of input types.

Are any of these open source?

Yes, both publish their weights (Llama 3.2 Community License), so you can self-host them.

Which is newer?

Gemma 3 4B IT is the newest, released Mar 12, 2025. Llama-3.2-90B-Vision-Instruct came out Sep 25, 2024. Knowledge cutoff: Llama-3.2-90B-Vision-Instruct Dec 2023, Gemma 3 4B IT Aug 2024.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.

05 — Keep comparing

Related comparisons