gemma3:1b
OLLAMA GGUFgemma3 · 999.89M · Q4_K_M
Feb 28, 2026 · Apple M4
qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 6, 2026 · Apple M4 Pro
Global Score
68 vs 62
Hardware Fit
98 vs 35
Quality Score
55 vs 73
Hardware
gemma3:1b qwen3.5-4b-mlx
MachineMacBook AirMac mini
CPUApple M4Apple M4 Pro
Cores1014
RAM32 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modeunknownbalanced
Performance
gemma3:1b qwen3.5-4b-mlx
Tokens/sec39.40.0
First chunkN/A5548 ms
TTFT362 ms5.5 s
Load time0.3 sN/A
Memory usage1.3 GB2.9 GB
Memory %4%5%
HW Fit Score Breakdown
gemma3:1b
Speed
40/50
TTFT
30/20
Memory
28/30
qwen3.5-4b-mlx
Speed
0/50
TTFT
6/20
Memory
29/30
Quality
gemma3:1b
Reasoning
6/20
Coding
13/20
Instruction
15/20
Structured
12/15
Math
1/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
qwen3.5-4b-mlx
Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate 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