gemma-3-4b-it-q4-k-m
OLLAMA GGUFllama · 4B · Q4_K_M
Jul 9, 2026 · Intel Core™ i5-10400
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
80 vs 85
Hardware Fit
100 vs 95
Quality Score
71 vs 81
Hardware
gemma-3-4b-it-q4-k-m gemma4:e4b-mlx
MachineMac ProMacBook Pro
CPUIntel Core™ i5-10400Apple M2 Pro
Cores1210
RAM32 GB16 GB
GPUAMD Radeon RX 6700 XTApple M2 Pro
OSmacOS 26.5.1macOS 26.5
Archx64arm64
Power Modebalancedbalanced
Performance
gemma-3-4b-it-q4-k-m gemma4:e4b-mlx
Tokens/sec75.047.3
First chunk136 ms258 ms
TTFT136 ms258 ms
Load time0.0 s5.1 s
Memory usage0.8 GB7.9 GB
Memory %3%49%
HW Fit Score Breakdown
gemma-3-4b-it-q4-k-m
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
Quality
gemma-3-4b-it-q4-k-m
Reasoning
11/20
Coding
17/20
Instruction
14/20
Structured
14/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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
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