Back to leaderboard

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

Global Score
82 vs 87
Hardware Fit
88 vs 81
Quality Score
80 vs 90

Hardware

unsloth-phi-4 GPT-20B:20b
MachineMac miniHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M4 ProAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1432
RAM64 GB31 GB
GPUApple M4 ProAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 15.7.4Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

unsloth-phi-4 GPT-20B:20b
Tokens/sec27.436.9
First chunk457 ms902 ms
TTFT457 ms4.2 s
Load timeN/A19.5 s
Memory usage7.7 GB13.1 GB
Memory %12%42%

HW Fit Score Breakdown

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

GPT-20B:20b

Speed
47/50
TTFT
7/20
Memory
27/30

Quality

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

GPT-20B:20b

Reasoning
19/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View unsloth-phi-4 details | View GPT-20B:20b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest