phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
nemotron-3-nano:latest
OLLAMA GGUFnemotron_h_moe · 31.6B · Q4_K_M
Mar 27, 2026 · AMD RYZEN AI MAX+ 395
Global Score
85 vs 89
Hardware Fit
100 vs 100
Quality Score
79 vs 84
Hardware
phi4:latest nemotron-3-nano:la…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4AZW GTR Pro
CPUIntel Core™ i5-14400FAMD RYZEN AI MAX+ 395
Cores1632
RAM32 GB125 GB
GPUNVIDIA GeForce RTX 5060 TiRadeon 8060S
OSMicrosoft Windows 11 Professionnel 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedperformance
Performance
phi4:latest nemotron-3-nano:la…
Tokens/sec38.365.2
First chunk72 ms295 ms
TTFT72 ms295 ms
Load time6.2 s8.7 s
Memory usage9.1 GB26.0 GB
Memory %29%21%
HW Fit Score Breakdown
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
nemotron-3-nano:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
phi4:latest
Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
nemotron-3-nano:latest
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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