Back to leaderboard

qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

qwen2.5:0.5b

qwen2 · 494.03M · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

Global Score
61 vs 57
Hardware Fit
100 vs 100
Quality Score
44 vs 39

Hardware

qwen3:0.6b qwen2.5:0.5b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3:0.6b qwen2.5:0.5b
Tokens/sec144.3165.0
TTFT81 ms81 ms
Load time0.9 s0.5 s
Memory usage4.1 GB1.7 GB
Memory %13%5%

HW Fit Score Breakdown

qwen3:0.6b

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

qwen2.5:0.5b

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

Quality

qwen3:0.6b

Reasoning
6/20
Coding
4/20
Instruction
10/20
Structured
13/15
Math
6/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Weak

qwen2.5:0.5b

Reasoning
6/20
Coding
6/20
Instruction
7/20
Structured
11/15
Math
5/15
Multilingual
4/10
Reasoning: Weak Coding: Weak Instruction Following: Weak Structured Output: Adequate Math: Weak Multilingual: Weak
View qwen3:0.6b details | View qwen2.5:0.5b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running