Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Excellent

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

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
82 vs 65
Hardware Fit
93 vs 88
Quality Score
77 vs 55

Hardware

qwen3.5:4b qwen3.5-2b-mlx
MachineAZW GTR ProMac mini
CPUAMD RYZEN AI MAX+ 395 w/ Radeon 8060SApple M4 Pro
Cores3214
RAM125 GB64 GB
GPUIntegrated / Apple SiliconApple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archx64arm64
Power Modeperformancebalanced

Performance

qwen3.5:4b qwen3.5-2b-mlx
Tokens/sec46.848.9
First chunk174 ms4208 ms
TTFT174 ms4.2 s
Load time5.9 sN/A
Memory usage16.2 GB1.6 GB
Memory %13%3%

HW Fit Score Breakdown

qwen3.5:4b

Speed
43/50
TTFT
20/20
Memory
30/30

qwen3.5-2b-mlx

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

Quality

qwen3.5:4b

Reasoning
15/20
Coding
14/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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
View qwen3.5:4b details | View qwen3.5-2b-mlx 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