Back to leaderboard

deepseek-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

starcoder2:3b

OLLAMA GGUF

starcoder2 · 3B · Q4_0

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score
69 vs 35
Hardware Fit
100 vs 100
Quality Score
55 vs 7

Hardware

deepseek-v2:16b starcoder2:3b
MachineMacBook AirNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4Cortex-A78AE
Cores106
RAM32 GB7 GB
GPUApple M4Integrated / Unknown
OSmacOS 26.3Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

deepseek-v2:16b starcoder2:3b
Tokens/sec56.631.5
First chunkN/A392 ms
TTFT239 ms392 ms
Load time1.2 s4.8 s
Memory usage17.7 GB1.8 GB
Memory %55%24%

HW Fit Score Breakdown

deepseek-v2:16b

Speed
40/50
TTFT
30/20
Memory
30/30

starcoder2:3b

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

Quality

deepseek-v2:16b

Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
10/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

starcoder2:3b

Reasoning
0/20
Coding
3/20
Instruction
1/20
Structured
0/15
Math
1/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

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