qwen3.5-2b-mlx

qwen3_5 · 2B · 8bit

Marginal

Mar 3, 2026 · Apple M4

qwen2.5:0.5b

qwen2 · 494.03M · Q4_K_M

Marginal

Mar 2, 2026 · Apple M4

Global Score

49 vs 57

Hardware Fit

83 vs 100

Quality Score

35 vs 39

Hardware

qwen3.5-2b-mlx 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

qwen3.5-2b-mlx qwen2.5:0.5b

Tokens/sec18.6165.0

TTFT2.9 s81 ms

Load time0.0 s0.5 s

Memory usage0.0 GB1.7 GB

Memory %0%5%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed

31/40

TTFT

22/30

Memory

30/30

qwen2.5:0.5b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

qwen3.5-2b-mlx

Reasoning

0/20

Coding

9/20

Instruction

10/20

Structured

4/15

Math

3/15

Multilingual

9/10

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

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 qwen3.5-2b-mlx details | View qwen2.5:0.5b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running