Back to leaderboard

phi3:14b

phi3 · 14.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

mistral:7b

llama · 7.2B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

Global Score
63 vs 58
Hardware Fit
83 vs 81
Quality Score
55 vs 48

Hardware

phi3:14b mistral:7b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedunknown

Performance

phi3:14b mistral:7b
Tokens/sec12.713.6
TTFT434 ms517 ms
Load time0.9 s3.0 s
Memory usage17.7 GB10.1 GB
Memory %55%32%

HW Fit Score Breakdown

phi3:14b

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

mistral:7b

Speed
21/40
TTFT
30/30
Memory
30/30

Quality

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

mistral:7b

Reasoning
8/20
Coding
0/20
Instruction
12/20
Structured
14/15
Math
5/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View phi3:14b details | View mistral:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running