Back to leaderboard

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

qwen2.5:1.5b

qwen2 · 1.5B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
65 vs 70
Hardware Fit
99 vs 100
Quality Score
51 vs 57

Hardware

qwen3.5:0.8b qwen2.5:1.5b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:0.8b qwen2.5:1.5b
Tokens/sec48.284.1
TTFT195 ms119 ms
Load time1.0 s0.5 s
Memory usage2.5 GB2.6 GB
Memory %8%8%

HW Fit Score Breakdown

qwen3.5:0.8b

Speed
40/40
TTFT
30/30
Memory
29/30

qwen2.5:1.5b

Speed
40/40
TTFT
30/30
Memory
30/30

Quality

qwen3.5:0.8b

Reasoning
9/20
Coding
6/20
Instruction
11/20
Structured
13/15
Math
5/15
Multilingual
7/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate

qwen2.5:1.5b

Reasoning
8/20
Coding
10/20
Instruction
12/20
Structured
13/15
Math
6/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3.5:0.8b details | View qwen2.5:1.5b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running