qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

mistral:latest

OLLAMA GGUF

llama · 7.2B · Q4_0

Good

Feb 28, 2026 · Apple M4 Pro

Global Score

70 vs 72

Hardware Fit

93 vs 100

Quality Score

60 vs 60

Hardware

qwen3.5-2b-mlx mistral:latest

MachineMacBook AirMac Mini

CPUApple M4Apple M4 Pro

Cores1014

RAM32 GB64 GB

GPUApple M4Apple M4 Pro

OSmacOS 26.3macOS 15.7.4

Archarm64arm64

Power Modebalancedunknown

Performance

qwen3.5-2b-mlx mistral:latest

Tokens/sec32.954.3

First chunk3096 msN/A

TTFT3.1 s124 ms

Load timeN/A0.0 s

Memory usage2.5 GB9.9 GB

Memory %8%15%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed

50/50

TTFT

13/20

Memory

30/30

mistral:latest

Speed

40/50

TTFT

30/20

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

mistral:latest

Reasoning

8/20

Coding

15/20

Instruction

13/20

Structured

12/15

Math

3/15

Multilingual

9/10

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

View qwen3.5-2b-mlx details | View mistral:latest 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