qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

qwen2.5-coder:1.5b

OLLAMA GGUF

qwen2 · 1.5B · Q4_K_M

Good

Aug 28, 2026 · Intel Core™ i5-10210U

Global Score

70 vs 68

Hardware Fit

93 vs 100

Quality Score

60 vs 54

Hardware

qwen3.5-2b-mlx qwen2.5-coder:1.5b

MachineMacBook AirLENOVO 20U30029MB

CPUApple M4Intel Core™ i5-10210U

Cores108

RAM32 GB15 GB

GPUApple M4CometLake-U GT2 [UHD Graphics]

OSmacOS 26.3Pop 24.04 LTS

Archarm64x64

Power Modebalancedlow-power

Performance

qwen3.5-2b-mlx qwen2.5-coder:1.5b

Tokens/sec32.921.8

First chunk3096 ms499 ms

TTFT3.1 s499 ms

Load timeN/A4.4 s

Memory usage2.5 GB1.5 GB

Memory %8%10%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed

50/50

TTFT

13/20

Memory

30/30

qwen2.5-coder:1.5b

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

qwen3.5-2b-mlx

Reasoning

11/20

Coding

9/20

Instruction

14/20

Structured

14/15

Math

3/15

Multilingual

9/10

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

qwen2.5-coder:1.5b

Reasoning

8/20

Coding

11/20

Instruction

13/20

Structured

11/15

Math

3/15

Multilingual

8/10

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

View qwen3.5-2b-mlx details | View qwen2.5-coder:1.5b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest