Skip to main content
Back to Explore

Llama 3.2 Instruct 11B (Vision)

Meta·Released 2024-09-25
Open SourceMultimodal
Compare

Related Models

Meta: Llama Guard 4 12B2025-04-30Meta: Llama Guard 4 12B (free)2025-04-30Meta: Llama 4 Maverick2025-04-05Meta: Llama 4 Scout2025-04-05Llama 4 Scout 17B 16E Instruct2025-04-02Llama Guard 3 8B2025-02-12Llama 3.3 Instruct 70B2024-12-06Meta: Llama 3.3 70B Instruct2024-12-06

Pricing

Input

$0.24

per 1M tokens

Output

$0.24

per 1M tokens

Blended

$0.24

per 1M tokens

Cheaper than 67% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.24

Monthly

$7.35

vs. Similar Models

Gemma 3 12B InstructQ:+0.1
$0.14-43%
Llama 3 Instruct 70BQ:+0.2
$1.18+380%
Microsoft: Phi 4 Mini InstructQ:-0.3
$0.15-40%
Command-R+ (Apr '24)Q:-0.3
$6.00+2349%

Performance

87

tokens/sec

Faster than 46% of models

0.49

seconds

Faster than 87% of models

0.49

seconds

Faster than 91% of models

Market Median

94 tok/s

8% slower

Median TTFT

1.12s

56% faster

Throughput/Dollar

353

tok/s per $/1M

Speed Comparison

OpenAI: GPT-5.2
87 tok/s-0%
Llama 3.2 Instruct 1B
87 tok/s+0%
Ring-flash-2.0
86 tok/s-0%

Benchmarks

MMLU-Pro
46.4%
GPQA Diamond
22.1%
HLE
5.2%
LiveCodeBench
11.0%
SciCode
11.2%
TerminalBench Hard
0.8%
MATH-500
51.6%
AIME
9.3%
AIME 2025
1.7%
IFBench
30.4%
Long Context Recall
11.7%
Tau2
14.6%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

PALM-2

Google

Q: 3.2N/A/1M

Granite 4.1 3B

IBM

Q: 3.2N/A/1M

Gemma 3 12B Instruct

Google

Q: 3.4$0.14/1M
Slower: 70%Cheaper: 43%

LFM 40B

Liquid AI

Q: 3.4N/A/1M

Arctic Instruct

Snowflake

Q: 3.4N/A/1M

Qwen Chat 72B

Alibaba

Q: 3.4N/A/1M
Compare all 7 models