deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
gemma4:e4b-mlx
OLLAMA GGUFJul 7, 2026 · Apple M2 Pro
Global Score
64 vs 78
Hardware Fit
98 vs 72
Quality Score
49 vs 81
Hardware
deepscaler:1.5b gemma4:e4b-mlx
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M2 Pro
Cores1210
RAM8 GB16 GB
GPUIntegrated / UnknownApple M2 Pro
OSUbuntu 26.04.1 LTSmacOS 26.5
Archx64arm64
Power Modeunknownbalanced
Performance
deepscaler:1.5b gemma4:e4b-mlx
Tokens/sec104.626.9
First chunk849 ms222 ms
TTFT850 ms222 ms
Load time10.5 s0.1 s
Memory usage3.0 GB15.4 GB
Memory %40%96%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
gemma4:e4b-mlx
Speed
50/50
TTFT
20/20
Memory
2/30
Quality
deepscaler:1.5b
Reasoning
10/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
11/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Weak
gemma4:e4b-mlx
Reasoning
14/20
Coding
19/20
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