gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
qwen/qwen3-30b-a3b-2507
LM-STUDIO GGUFqwen3moe · 30B · Q4_K_M
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
85 vs 90
Hardware Fit
95 vs 86
Quality Score
81 vs 91
Hardware
gemma4:e4b-mlx qwen/qwen3-30b-a3b…
MachineMacBook ProASUS
CPUApple M2 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1016
RAM16 GB31 GB
GPUApple M2 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 26.5cachyos rolling
Archarm64x64
Power Modebalancedperformance
Performance
gemma4:e4b-mlx qwen/qwen3-30b-a3b…
Tokens/sec47.3157.5
First chunk258 ms3 ms
TTFT258 ms114 ms
Load time5.1 sN/A
Memory usage7.9 GB21.0 GB
Memory %49%69%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
qwen/qwen3-30b-a3b-2507
Speed
50/50
TTFT
20/20
Memory
16/30
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
qwen/qwen3-30b-a3b-2507
Reasoning
18/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest