Back to leaderboard

qwen3.6-27b-mtp-pi-reasoning

LM-STUDIO GGUF

qwen35 · 27B · Q4_K_M

Excellent

Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
85 vs 82
Hardware Fit
80 vs 71
Quality Score
87 vs 87

Hardware

qwen3.6-27b-mtp-pi… qwen3-coder:30b
MachineASUSHP HP Pavilion Laptop 15-eh1xxx
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorAMD Ryzen 5 5500U
Cores1612
RAM31 GB63 GB
GPUNVIDIA GeForce RTX 4090, RaphaelAMD Radeon(TM) Graphics
OScachyos rollingMicrosoft Windows 10 Enterprise LTSC 10.0.19044
Archx64x64
Power Modelow-powerbalanced

Performance

qwen3.6-27b-mtp-pi… qwen3-coder:30b
Tokens/sec78.514.3
First chunk5 ms869 ms
TTFT198 ms869 ms
Load timeN/A0.3 s
Memory usage24.6 GB20.5 GB
Memory %81%32%

HW Fit Score Breakdown

qwen3.6-27b-mtp-pi-reas…

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

qwen3-coder:30b

Speed
22/50
TTFT
20/20
Memory
29/30

Quality

qwen3.6-27b-mtp-pi-reas…

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-coder:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3.6-27b-mtp-pi… details | View qwen3-coder:30b 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