phi-3-mini-128k-instruct
LM-STUDIO MLXphi3 · 4bit
Mar 4, 2026 · Apple M4
Qwen3-80B:80B
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
38 vs 62
Hardware Fit
100 vs 10
Quality Score
12 vs 84
Hardware
phi-3-mini-128k-in… Qwen3-80B:80B
MachineMacBook AirHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M4AMD Ryzen 9 9955HX3D 16-Core Processor
Cores1032
RAM32 GB31 GB
GPUApple M4AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 26.3Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
phi-3-mini-128k-in… Qwen3-80B:80B
Tokens/sec44.04.9
First chunk384 ms8006 ms
TTFT385 ms8.0 s
Load timeN/A63.7 s
Memory usage2.0 GB47.3 GB
Memory %6%153%
HW Fit Score Breakdown
phi-3-mini-128k-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
Qwen3-80B:80B
Speed
6/50
TTFT
4/20
Memory
0/30
Quality
phi-3-mini-128k-instruct
Reasoning
3/20
Coding
2/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
Qwen3-80B:80B
Reasoning
17/20
Coding
19/20
Instruction
13/20
Structured
13/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong 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