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

qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
85 vs 79
Hardware Fit
80 vs 59
Quality Score
87 vs 87

Hardware

qwen3.6-27b-mtp-pi… qwen3.6-35b-a3b
MachineASUSDocker Container
CPUAMD Ryzen 7 7800X3D 8-Core ProcessorIntel Gen Intel® Core™ i9-11900H
Cores1616
RAM31 GB15 GB
GPUNVIDIA GeForce RTX 4090, RaphaelTigerLake-H GT1 [UHD Graphics]
OScachyos rollingUbuntu 26.04 LTS
Archx64x64
Power Modeperformanceperformance

Performance

qwen3.6-27b-mtp-pi… qwen3.6-35b-a3b
Tokens/sec42.29.3
First chunk33 ms21 ms
TTFT366 ms3.6 s
Load timeN/A32.0 s
Memory usage24.6 GB1.8 GB
Memory %81%12%

HW Fit Score Breakdown

qwen3.6-27b-mtp-pi-reas…

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

qwen3.6-35b-a3b

Speed
17/50
TTFT
12/20
Memory
30/30

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

qwen3.6-35b-a3b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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