Back to leaderboard

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

qwopus3.6-27b-coder-compat-mtp

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

Global Score
82 vs 88
Hardware Fit
88 vs 80
Quality Score
80 vs 91

Hardware

unsloth-phi-4 qwopus3.6-27b-code…
MachineMac miniASUS
CPUApple M4 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1416
RAM64 GB31 GB
GPUApple M4 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 15.7.4cachyos rolling
Archarm64x64
Power Modebalancedperformance

Performance

unsloth-phi-4 qwopus3.6-27b-code…
Tokens/sec27.480.8
First chunk457 ms6 ms
TTFT457 ms226 ms
Load timeN/AN/A
Memory usage7.7 GB24.6 GB
Memory %12%81%

HW Fit Score Breakdown

unsloth-phi-4

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

qwopus3.6-27b-coder-com…

Speed
50/50
TTFT
20/20
Memory
10/30

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

qwopus3.6-27b-coder-com…

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View unsloth-phi-4 details | View qwopus3.6-27b-code… 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