qwen2.5:0.5b

qwen2 · 494.03M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

tinyllama:1.1b

llama · 1B · Q4_0

Marginal

Mar 1, 2026 · Apple M4

Global Score

63 vs 50

Hardware Fit

100 vs 99

Quality Score

39 vs 18

Hardware

qwen2.5:0.5b tinyllama:1.1b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen2.5:0.5b tinyllama:1.1b

Tokens/sec165.0129.6

TTFT81 ms58 ms

Load time0.5 s0.4 s

Memory usage1.7 GB0.7 GB

Memory %5%2%

HW Fit Score Breakdown

qwen2.5:0.5b

Speed

40/40

TTFT

30/30

Memory

30/30

tinyllama:1.1b

Speed

40/40

TTFT

30/30

Memory

29/30

Quality

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

tinyllama:1.1b

Reasoning

2/20

Coding

0/20

Instruction

6/20

Structured

7/15

Math

0/15

Multilingual

3/10

Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak

View qwen2.5:0.5b details | View tinyllama:1.1b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running