dolphin-phi:2.7b
OLLAMA GGUFphi2 · 3B · Q4_0
Mar 1, 2026 · Apple M4
qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 18, 2026 · Intel Xeon® E5-2637 v3
Global Score
61 vs 78
Hardware Fit
100 vs 51
Quality Score
44 vs 89
Hardware
dolphin-phi:2.7b qwen3-next:80b-a3b…
MachineMacBook AirDell Inc. Precision Tower 7910
CPUApple M4Intel Xeon® E5-2637 v3
Cores1016
RAM32 GB96 GB
GPUApple M4NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSmacOS 26.3Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
dolphin-phi:2.7b qwen3-next:80b-a3b…
Tokens/sec56.18.7
First chunkN/A1251 ms
TTFT108 ms1.3 s
Load time0.4 s61.6 s
Memory usage2.2 GB48.3 GB
Memory %7%50%
HW Fit Score Breakdown
dolphin-phi:2.7b
Speed
40/50
TTFT
30/20
Memory
30/30
qwen3-next:80b-a3b-inst…
Speed
9/50
TTFT
17/20
Memory
25/30
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-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest