Back to leaderboard

qwen2.5-7b-instruct

LM-STUDIO MLX

qwen2 · 7B · 4bit

Excellent

Mar 3, 2026 · Apple M4

gemma3:1b

OLLAMA GGUF

gemma3 · 999.89M · Q4_K_M

Marginal

Jun 25, 2026 · Cortex-A78AE

Global Score
82 vs 59
Hardware Fit
92 vs 100
Quality Score
78 vs 42

Hardware

qwen2.5-7b-instruct gemma3:1b
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

qwen2.5-7b-instruct gemma3:1b
Tokens/sec22.034.0
First chunk477 ms1876 ms
TTFT477 ms1.9 s
Load timeN/A1.7 s
Memory usage4.0 GB0.8 GB
Memory %13%11%

HW Fit Score Breakdown

qwen2.5-7b-instruct

Speed
43/50
TTFT
20/20
Memory
29/30

gemma3:1b

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

Quality

qwen2.5-7b-instruct

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma3:1b

Reasoning
7/20
Coding
5/20
Instruction
15/20
Structured
7/15
Math
1/15
Multilingual
7/10
Reasoning: Weak Coding: Poor Instruction Following: Strong Structured Output: Weak Math: Poor Multilingual: Adequate

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