Back to leaderboard

smollm2-360m-instruct

LM-STUDIO MLX

llama · 360M · bf16

Marginal

Mar 4, 2026 · Apple M4

phi3:14b

OLLAMA GGUF

phi3 · 14.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score
52 vs 63
Hardware Fit
100 vs 83
Quality Score
32 vs 55

Hardware

smollm2-360m-instr… phi3:14b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

smollm2-360m-instr… phi3:14b
Tokens/sec121.112.7
First chunk106 msN/A
TTFT106 ms434 ms
Load timeN/A0.9 s
Memory usage0.7 GB17.7 GB
Memory %2%55%

HW Fit Score Breakdown

smollm2-360m-instruct

Speed
50/50
TTFT
20/20
Memory
30/30

phi3:14b

Speed
23/50
TTFT
30/20
Memory
30/30

Quality

smollm2-360m-instruct

Reasoning
4/20
Coding
3/20
Instruction
12/20
Structured
7/15
Math
2/15
Multilingual
4/10
Reasoning: Poor Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Weak

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 smollm2-360m-instr… details | View phi3:14b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest