mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
80 vs 60
Hardware Fit
100 vs 90
Quality Score
71 vs 47
Hardware
mlx-community/gemm… deepseek-r1:1.5b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/gemm… deepseek-r1:1.5b
Tokens/sec43.234.6
First chunk428 ms5314 ms
TTFT428 ms5.3 s
Load timeN/A5.1 s
Memory usage1.3 GB1.1 GB
Memory %4%15%
HW Fit Score Breakdown
mlx-community/gemma-3-4…
Speed
50/50
TTFT
20/20
Memory
30/30
deepseek-r1:1.5b
Speed
50/50
TTFT
10/20
Memory
30/30
Quality
mlx-community/gemma-3-4…
Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
deepseek-r1:1.5b
Reasoning
11/20
Coding
6/20
Instruction
7/20
Structured
4/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong 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