Llama 3.1 Instruct 8B

Meta·Released 2024-07-23

Open SourceMultimodal

Model Family

Meta: Llama Guard 4 12B2025-04-30 Llama 4 Maverick2025-04-05 Llama 4 Scout2025-04-05 Llama 4 Scout 17B 16E Instruct2025-04-02 Llama Guard 3 8B2025-02-12 Llama 3.3 Instruct 70B2024-12-06 Meta: Llama 3.3 70B Instruct2024-12-06 Meta: Llama 3.3 70B Instruct (free)2024-12-06

Quality Index

11.8

336th of 442

Top 76%

Coding Index

4.9

306th of 352

Top 87%

Math Index

4.3

248th of 268

Top 93%

Price/1M

$0.10

226th cheapest

68% below median

Top 34%

Speed

198 tok/s

Top 8%

TTFT

0.45s

Market Position

Llama 3.1 Instruct 8BMarket Average

Pricing

Input

$0.10

per 1M tokens

Output

$0.10

per 1M tokens

Blended

$0.10

per 1M tokens

Cheaper than 66% of models. Median price is $0.31/1M tokens.

Cost Calculator

Tokens per day1M

100K100M

Daily

$0.10

Monthly

$3.00

vs. Similar Models

Llama 3.2 Instruct 90B (Vision)Q:+0.1

$0.72+620%

Solar MiniQ:+0.1

$0.15+50%

EXAONE 4.0 32B (Non-reasoning)Q:-0.1

$0.00-100%

Grok-1Q:-0.1

$0.00-100%

Performance

198

tokens/sec

Faster than 92% of models

0.45

seconds

Faster than 47% of models

0.45

seconds

Faster than 50% of models

Market Median

46 tok/s

335% faster

Median TTFT

0.42s

7% slower

Throughput/Dollar

1983

tok/s per $/1M

Speed Comparison

Grok 3 mini Reasoning (high)

198 tok/s-0%

GPT-5.1 Codex mini (high)

199 tok/s+0%

Devstral Small 2

204 tok/s+3%

Benchmarks

MMLU-Pro

47.6%

GPQA Diamond

25.9%

HLE

5.1%

LiveCodeBench

11.6%

SciCode

13.2%

TerminalBench Hard

0.8%

MATH-500

51.9%

AIME

7.7%

AIME 2025

4.3%

IFBench

28.6%

Long Context Recall

15.7%

Tau2

16.4%

Market AverageTop Score

Open Source

Quick Compare

Similar Models

Llama 3.2 Instruct 90B (Vision)