Back to leaderboard

deepseek-coder:6.7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

phi4-mini:latest

phi3 · 3.8B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score
63 vs 75
Hardware Fit
98 vs 100
Quality Score
39 vs 58

Hardware

deepseek-coder:6.7b phi4-mini:latest
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

deepseek-coder:6.7b phi4-mini:latest
Tokens/sec24.136.2
TTFT251 ms190 ms
Load time0.9 s0.8 s
Memory usage12.6 GB8.3 GB
Memory %39%26%

HW Fit Score Breakdown

deepseek-coder:6.7b

Speed
38/40
TTFT
30/30
Memory
30/30

phi4-mini:latest

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

Quality

deepseek-coder:6.7b

Reasoning
4/20
Coding
14/20
Instruction
9/20
Structured
6/15
Math
1/15
Multilingual
5/10
Reasoning: Poor Coding: Adequate Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak

phi4-mini:latest

Reasoning
12/20
Coding
10/20
Instruction
10/20
Structured
11/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong
View deepseek-coder:6.7b details | View phi4-mini:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running