phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
85 vs 66
Hardware Fit
100 vs 99
Quality Score
79 vs 52
Hardware
phi4:latest granite3.1-moe:3b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Dell Inc. Inspiron 15 3530
CPUIntel Core™ i5-14400FIntel Gen Intel® Core™ i7-1355U
Cores1612
RAM32 GB31 GB
GPUNVIDIA GeForce RTX 5060 TiRaptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Professionnel 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
phi4:latest granite3.1-moe:3b
Tokens/sec38.327.2
First chunk72 ms527 ms
TTFT72 ms527 ms
Load time6.2 s1.9 s
Memory usage9.1 GB2.9 GB
Memory %29%9%
HW Fit Score Breakdown
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
granite3.1-moe:3b
Speed
49/50
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
granite3.1-moe:3b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
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