Back to leaderboard

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 6, 2026 · AMD RYZEN AI MAX+ 395 w/ Radeon 8060S

Global Score
65 vs 82
Hardware Fit
88 vs 81
Quality Score
55 vs 82

Hardware

qwen3.5-2b-mlx qwen3.5:9b
MachineMac miniAZW GTR Pro
CPUApple M4 ProAMD RYZEN AI MAX+ 395 w/ Radeon 8060S
Cores1432
RAM64 GB125 GB
GPUApple M4 ProIntegrated / Apple Silicon
OSmacOS 15.7.4Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5-2b-mlx qwen3.5:9b
Tokens/sec48.930.8
First chunk4208 ms195 ms
TTFT4.2 s195 ms
Load timeN/A6.8 s
Memory usage1.6 GB18.8 GB
Memory %3%15%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

Quality

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5-2b-mlx details | View qwen3.5:9b 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