llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
phi4:14b
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
72 vs 77
Hardware Fit
77 vs 74
Quality Score
70 vs 78
Hardware
llama3.1:8b phi4:14b
MachineMacBook ProNVIDIA NVIDIA_DGX_Spark
CPUApple M1 ProCortex-X925
Cores1020
RAM16 GB122 GB
GPUApple M1 ProDevice 2e12
OSmacOS 26.6.2Ubuntu 24.04.4 LTS
Archarm64arm64
Power Modebalancedperformance
Performance
llama3.1:8b phi4:14b
Tokens/sec21.522.9
First chunk368 ms198 ms
TTFT368 ms198 ms
Load time6.9 s10.3 s
Memory usage12.9 GB14.7 GB
Memory %81%12%
HW Fit Score Breakdown
llama3.1:8b
Speed
47/50
TTFT
20/20
Memory
10/30
phi4:14b
Speed
24/50
TTFT
20/20
Memory
30/30
Quality
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
phi4:14b
Reasoning
18/20
Coding
18/20
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
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