Back to leaderboard

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

gemma4:e4b-mlx

OLLAMA GGUF
Excellent

Jul 7, 2026 · Apple M2 Pro

Global Score
59 vs 85
Hardware Fit
69 vs 95
Quality Score
54 vs 81

Hardware

qwen3.5:35b-a3b gemma4:e4b-mlx
MachineMacBook ProMacBook Pro
CPUApple M4 ProApple M2 Pro
Cores1410
RAM48 GB16 GB
GPUApple M4 ProApple M2 Pro
OSmacOS 26.3.1macOS 26.5
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b gemma4:e4b-mlx
Tokens/sec30.547.3
First chunk333 ms258 ms
TTFT30.0 s258 ms
Load time9.8 s5.1 s
Memory usage25.1 GB7.9 GB
Memory %52%49%

HW Fit Score Breakdown

qwen3.5:35b-a3b

Speed
45/50
TTFT
0/20
Memory
24/30

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
25/30

Quality

qwen3.5:35b-a3b

Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong

gemma4:e4b-mlx

Reasoning
15/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:35b-a3b details | View gemma4:e4b-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