deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
gemma4:12b-mlx
OLLAMA GGUFAug 24, 2026 · Apple M1 Pro
Global Score
37 vs 71
Hardware Fit
73 vs 76
Quality Score
22 vs 69
Hardware
deepseek-r1:1.5b gemma4:12b-mlx
MachineLENOVO 20L7CTO1WWMacBook Pro
CPUIntel Core™ i5-8350UApple M1 Pro
Cores810
RAM23 GB16 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Apple M1 Pro
OSFedora Linux 43macOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced
Performance
deepseek-r1:1.5b gemma4:12b-mlx
Tokens/sec18.425.0
First chunk593 ms787 ms
TTFT30.0 s30.0 s
Load time3.8 s4.0 s
Memory usage1.0 GB7.1 GB
Memory %4%45%
HW Fit Score Breakdown
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
0/20
Memory
26/30
Quality
deepseek-r1:1.5b
Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak
gemma4:12b-mlx
Reasoning
14/20
Coding
10/20
Instruction
9/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Weak 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