llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
81 vs 74
Hardware Fit
100 vs 98
Quality Score
73 vs 63
Hardware
llama-3.1-8b-instr… phi4-mini:latest
MachineASUSNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD Ryzen 5 5500Cortex-A78AE
Cores126
RAM31 GB7 GB
GPUNavi 44 [Radeon RX 9060 XT]Integrated / Unknown
OSNobara Linux 43Ubuntu 22.04.5 LTS
Archx64arm64
Power Modeperformancebalanced
Performance
llama-3.1-8b-instr… phi4-mini:latest
Tokens/sec35.618.4
First chunk52 ms1078 ms
TTFT256 ms1.1 s
Load timeN/A6.4 s
Memory usage8.6 GB2.9 GB
Memory %28%39%
HW Fit Score Breakdown
llama-3.1-8b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
phi4-mini:latest
Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate 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