phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
74 vs 68
Hardware Fit
98 vs 22
Quality Score
63 vs 88
Hardware
phi4-mini:latest qwen3.8:latest
MachineNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit SuperSystem manufacturer
CPUCortex-A78AEAMD Ryzen 9 5950X 16-Core Processor
Cores632
RAM7 GB32 GB
GPUIntegrated / UnknownNVIDIA GeForce RTX 3090
OSUbuntu 22.04.5 LTSMicrosoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
phi4-mini:latest qwen3.8:latest
Tokens/sec18.410.0
First chunk1078 ms1041 ms
TTFT1.1 s14.3 s
Load time6.4 s22.3 s
Memory usage2.9 GB26.2 GB
Memory %39%82%
HW Fit Score Breakdown
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
Quality
phi4-mini:latest
Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong
qwen3.8:latest
Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
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