Back to leaderboard

qwen2.5:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

qwen3.5-9b

LM-STUDIO GGUF

qwen35 · 9B · Q4_K_M

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
77 vs 72
Hardware Fit
100 vs 89
Quality Score
67 vs 65

Hardware

qwen2.5:3b qwen3.5-9b
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperMac mini
CPUCortex-A78AEApple M4 Pro
Cores614
RAM7 GB64 GB
GPUIntegrated / UnknownApple M4 Pro
OSUbuntu 22.04.5 LTSmacOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen2.5:3b qwen3.5-9b
Tokens/sec21.428.9
First chunk1006 ms338 ms
TTFT1.0 s338 ms
Load time6.4 sN/A
Memory usage2.0 GB6.1 GB
Memory %27%10%

HW Fit Score Breakdown

qwen2.5:3b

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

qwen3.5-9b

Speed
39/50
TTFT
20/20
Memory
30/30

Quality

qwen2.5:3b

Reasoning
12/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

qwen3.5-9b

Reasoning
17/20
Coding
15/20
Instruction
6/20
Structured
7/15
Math
12/15
Multilingual
8/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Weak Math: Strong 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