qwen3.5-0.8b-mlx
LM-STUDIO MLXqwen3_5 · 0.8B · 4bit
Mar 3, 2026 · Apple M4
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
55 vs 85
Hardware Fit
87 vs 95
Quality Score
41 vs 81
Hardware
qwen3.5-0.8b-mlx gemma4:e4b-mlx
MachineMacBook AirMacBook Pro
CPUApple M4Apple M2 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M2 Pro
OSmacOS 26.3macOS 26.5
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-0.8b-mlx gemma4:e4b-mlx
Tokens/sec68.247.3
First chunk3268 ms258 ms
TTFT3.3 s258 ms
Load timeN/A5.1 s
Memory usage0.6 GB7.9 GB
Memory %2%49%
HW Fit Score Breakdown
qwen3.5-0.8b-mlx
Speed
50/50
TTFT
13/20
Memory
24/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
25/30
Quality
qwen3.5-0.8b-mlx
Reasoning
8/20
Coding
1/20
Instruction
12/20
Structured
12/15
Math
3/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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