Back to leaderboard

deepseek-r1:14b

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 1, 2026 · Apple M4

phi3:14b

phi3 · 14.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
25 vs 66
Hardware Fit
46 vs 83
Quality Score
11 vs 55

Hardware

deepseek-r1:14b phi3:14b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modeunknownbalanced

Performance

deepseek-r1:14b phi3:14b
Tokens/sec10.812.7
TTFT30.0 s434 ms
Load time5.3 s0.9 s
Memory usage16.5 GB17.7 GB
Memory %52%55%

HW Fit Score Breakdown

deepseek-r1:14b

Speed
16/40
TTFT
0/30
Memory
30/30

phi3:14b

Speed
23/40
TTFT
30/30
Memory
30/30

Quality

deepseek-r1:14b

Reasoning
1/20
Coding
0/20
Instruction
2/20
Structured
1/15
Math
1/15
Multilingual
6/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate

phi3:14b

Reasoning
14/20
Coding
2/20
Instruction
14/20
Structured
7/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Adequate Multilingual: Strong
View deepseek-r1:14b details | View phi3:14b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running