phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
85 vs 72
Hardware Fit
100 vs 77
Quality Score
79 vs 70
Hardware
phi4:latest llama3.1:8b
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4MacBook Pro
CPUIntel Core™ i5-14400FApple M1 Pro
Cores1610
RAM32 GB16 GB
GPUNVIDIA GeForce RTX 5060 TiApple M1 Pro
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced
Performance
phi4:latest llama3.1:8b
Tokens/sec38.321.5
First chunk72 ms368 ms
TTFT72 ms368 ms
Load time6.2 s6.9 s
Memory usage9.1 GB12.9 GB
Memory %29%81%
HW Fit Score Breakdown
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
llama3.1:8b
Speed
47/50
TTFT
20/20
Memory
10/30
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
llama3.1:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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