Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Excellent

Jul 7, 2026 · Apple M2 Pro

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

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

Hardware

gemma4:e4b-mlx qwen3.5:35b-a3b
MachineMacBook ProMacBook Pro
CPUApple M2 ProApple M4 Pro
Cores1014
RAM16 GB48 GB
GPUApple M2 ProApple M4 Pro
OSmacOS 26.5macOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:e4b-mlx qwen3.5:35b-a3b
Tokens/sec47.330.5
First chunk258 ms333 ms
TTFT258 ms30.0 s
Load time5.1 s9.8 s
Memory usage7.9 GB25.1 GB
Memory %49%52%

HW Fit Score Breakdown

gemma4:e4b-mlx

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

qwen3.5:35b-a3b

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

Quality

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

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
View gemma4:e4b-mlx details | View qwen3.5:35b-a3b 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