Skip to main content
Back to Explore

Qwen3.5 0.8B

Alibaba·Released 2026-02-28
Open Source800MApache 2.0

Pricing

Input

$0.01

per 1M tokens

Output

$0.05

per 1M tokens

Blended

$0.02

per 1M tokens

Cheaper than 92% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.02

Monthly

$0.60

vs. Similar Models

Jamba 1.6 LargeQ:0.0
$3.50+17400%
Jamba 1.5 LargeQ:+0.1
$3.50+17400%
Nous: Hermes 3 70B InstructQ:+0.1
$0.70+3400%
Qwen3 8B (Non-reasoning)Q:+0.1
$0.18+825%

Performance

30

tokens/sec

Faster than 2% of models

0.59

seconds

Faster than 77% of models

67.00

seconds

Faster than 3% of models

Market Median

94 tok/s

68% slower

Median TTFT

1.11s

47% faster

Throughput/Dollar

1506

tok/s per $/1M

Speed Comparison

Qwen3.5 0.8B (Non-reasoning)
30 tok/s+1%
Nous: Hermes 3 70B Instruct
30 tok/s-1%
QwQ 32B
32 tok/s+7%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
11.1%
HLE
1.2%
LiveCodeBenchNot evaluated
SciCode
0.0%
TerminalBench Hard
0.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
21.5%
Long Context Recall
5.3%
Tau2
47.7%
Market AverageTop Score
apache-2.01B
Downloads

2.5M

Likes

598

VRAM (FP16)

4-8 GB

GPU

RTX 3060 / M1

Quick Compare

Similar Models

Compare all 7 models