Skip to content
Model Pareto

Llama 3.2 Instruct 11B (Vision)

MetaOpen weightsartificialanalysis.ai ↗
Input
$0.345/M tok
Output
$0.345/M tok
Blended
$0.345/M tok · 3:1
Speed
22tok/s
Context
128Ktokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Llama 3.2 Instruct 11B (Vision). Price = AA median host price.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
1× B200 180GB
BF16 weights
Throughput
~9,135 tok/s
many requests batched
Price
$0.094–0.84 /M tok
busy → light use
On your own machine
RTX 5090 32GB (int4, ~230 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • BF16 weights (10.7B params) + 25% KV-cache headroom ≈ 27 GB
  • 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~9,135 output tok/s aggregate at batch 256 (bandwidth-bound)
  • Blended 3:1 input:output; prefill ~49,679 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Writing & chat

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Llama 3.2 Instruct 11B (Vision)Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
~last of 12 (estimated)below measured range (<74.5%)
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #11Gemini 3.5 Flash-Lite74.5%
  4. ~#12Llama 3.2 Instruct 11B (Vision)Estimated<74.5%
No published score — estimated from related benchmarks
~last of 8 (estimated)below measured range (<75.8%)
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #7Muse Glimmer75.8%
  4. ~#8Llama 3.2 Instruct 11B (Vision)Estimated<75.8%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
  1. #1Claude Fable 5.273.4%
  2. #2GPT-6 Astra71.0%
  3. #24Mistral Large 39.0%
  4. ~#25Llama 3.2 Instruct 11B (Vision)Estimated<9.0%
No published score — estimated from related benchmarks

Hard reasoning

Agents

OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3Llama 3.2 Instruct 11B (Vision)Estimated53.8%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
~last of 91 (estimated)below measured range (<3.3%)
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #90Llama 4 Scout3.3%
  4. ~#91Llama 3.2 Instruct 11B (Vision)Estimated<3.3%
No published score — estimated from related benchmarks