Back to leaderboard

gemma4:e4b-mlx

OLLAMA GGUF
Not Rec.

Jul 7, 2026 · Apple M2 Pro

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Aug 20, 2026 · Apple M4 Max

Global Score
78 vs 96
Hardware Fit
72 vs 95
Quality Score
81 vs 96

Hardware

gemma4:e4b-mlx qwen3-30b-a3b-thin…
MachineMacBook ProMacBook Pro
CPUApple M2 ProApple M4 Max
Cores1016
RAM16 GB128 GB
GPUApple M2 ProApple M4 Max
OSmacOS 26.5macOS 26.5.2
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:e4b-mlx qwen3-30b-a3b-thin…
Tokens/sec26.9112.8
First chunk222 ms21 ms
TTFT222 ms1.5 s
Load time0.1 s3.5 s
Memory usage15.4 GB0.0 GB
Memory %96%0%

HW Fit Score Breakdown

gemma4:e4b-mlx

Speed
50/50
TTFT
20/20
Memory
2/30

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
15/20
Memory
30/30

Quality

gemma4:e4b-mlx

Reasoning
14/20
Coding
19/20
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

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma4:e4b-mlx details | View qwen3-30b-a3b-thin… 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