deepscaler:1.5b
OLLAMA GGUFqwen2 · 1.8B · F16
Oct 11, 2026 · AMD Ryzen 5 5500
gemma4:e4b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
64 vs 90
Hardware Fit
98 vs 86
Quality Score
49 vs 92
Hardware
deepscaler:1.5b gemma4:e4b-mlx
MachineMicrosoft WSLMacBook Pro
CPUAMD Ryzen 5 5500Apple M1 Pro
Cores1210
RAM8 GB16 GB
GPUIntegrated / UnknownApple M1 Pro
OSUbuntu 26.04.1 LTSmacOS 26.6.2
Archx64arm64
Power Modeunknownbalanced
Performance
deepscaler:1.5b gemma4:e4b-mlx
Tokens/sec104.641.8
First chunk849 ms359 ms
TTFT850 ms4.2 s
Load time10.5 s5.1 s
Memory usage3.0 GB7.9 GB
Memory %40%49%
HW Fit Score Breakdown
deepscaler:1.5b
Speed
50/50
TTFT
20/20
Memory
28/30
gemma4:e4b-mlx
Speed
50/50
TTFT
11/20
Memory
25/30
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
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong 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