gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
tinyllama:1.1b
OLLAMA GGUFllama · 1B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
85 vs 43
Hardware Fit
95 vs 100
Quality Score
81 vs 19
Hardware
gemma4:e4b-mlx tinyllama:1.1b
MachineMacBook ProMacBook Air
CPUApple M2 ProApple M4
Cores1010
RAM16 GB32 GB
GPUApple M2 ProApple M4
OSmacOS 26.5macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
gemma4:e4b-mlx tinyllama:1.1b
Tokens/sec47.3121.0
First chunk258 msN/A
TTFT258 ms82 ms
Load time5.1 s0.4 s
Memory usage7.9 GB0.7 GB
Memory %49%2%
HW Fit Score Breakdown
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
tinyllama:1.1b
Speed
40/50
TTFT
30/20
Memory
30/30
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
tinyllama:1.1b
Reasoning
2/20
Coding
1/20
Instruction
6/20
Structured
7/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
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