Back to leaderboard

dolphin-phi:2.7b

OLLAMA GGUF

phi2 · 3B · Q4_0

Good

Mar 1, 2026 · Apple M4

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Excellent

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
61 vs 82
Hardware Fit
100 vs 81
Quality Score
44 vs 82

Hardware

dolphin-phi:2.7b qwen3.5:9b
MachineMacBook AirAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M4AMD Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedperformance

Performance

dolphin-phi:2.7b qwen3.5:9b
Tokens/sec56.130.8
First chunkN/A195 ms
TTFT108 ms195 ms
Load time0.4 s5.2 s
Memory usage2.2 GB18.8 GB
Memory %7%15%

HW Fit Score Breakdown

dolphin-phi:2.7b

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

qwen3.5:9b

Speed
31/50
TTFT
20/20
Memory
30/30

Quality

dolphin-phi:2.7b

Reasoning
10/20
Coding
6/20
Instruction
12/20
Structured
2/15
Math
9/15
Multilingual
5/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Poor Math: Adequate Multilingual: Adequate

qwen3.5:9b

Reasoning
14/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View dolphin-phi:2.7b details | View qwen3.5:9b 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