Back to leaderboard

deepseek-v2:16b

OLLAMA GGUF

deepseek2 · 15.7B · Q4_0

Good

Mar 2, 2026 · Apple M4

llama3.2:3b

OLLAMA GGUF

llama · 3.2B · Q4_K_M

Good

Jun 25, 2026 · Cortex-A78AE

Global Score
69 vs 74
Hardware Fit
100 vs 99
Quality Score
55 vs 63

Hardware

deepseek-v2:16b llama3.2:3b
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 llama3.2:3b
Tokens/sec56.621.1
First chunkN/A1032 ms
TTFT239 ms1.0 s
Load time1.2 s8.4 s
Memory usage17.7 GB2.4 GB
Memory %55%32%

HW Fit Score Breakdown

deepseek-v2:16b

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

llama3.2:3b

Speed
50/50
TTFT
20/20
Memory
29/30

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

llama3.2:3b

Reasoning
10/20
Coding
14/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong

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