phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
64 vs 37
Hardware Fit
100 vs 73
Quality Score
48 vs 22
Hardware
phi3:3.8b deepseek-r1:1.5b
MachineMacBook AirLENOVO 20L7CTO1WW
CPUApple M4Intel Core™ i5-8350U
Cores108
RAM32 GB23 GB
GPUApple M4Kaby Lake-R GT2 [UHD Graphics 620]
OSmacOS 26.3Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power
Performance
phi3:3.8b deepseek-r1:1.5b
Tokens/sec42.018.4
First chunkN/A593 ms
TTFT142 ms30.0 s
Load time1.1 s3.8 s
Memory usage16.0 GB1.0 GB
Memory %50%4%
HW Fit Score Breakdown
phi3:3.8b
Speed
40/50
TTFT
30/20
Memory
30/30
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
Quality
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
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
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