llama3.3:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
73 vs 85
Hardware Fit
51 vs 100
Quality Score
83 vs 79
Hardware
llama3.3:70b phi4:latest
MachineNVIDIA NVIDIA_DGX_SparkGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUCortex-X925Intel Core™ i5-14400F
Cores2016
RAM122 GB32 GB
GPUDevice 2e12NVIDIA GeForce RTX 5060 Ti
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
llama3.3:70b phi4:latest
Tokens/sec4.638.3
First chunk560 ms72 ms
TTFT560 ms72 ms
Load time13.8 s6.2 s
Memory usage49.5 GB9.1 GB
Memory %41%29%
HW Fit Score Breakdown
llama3.3:70b
Speed
4/50
TTFT
20/20
Memory
27/30
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
llama3.3:70b
Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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
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