Back to leaderboard

Gemma4-31B:31B

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Aug 18, 2026 · Intel Core™ Ultra X7 358H

qwen3.6-27b-mtp

LM-STUDIO GGUF

qwen35 · 27B · Q5_K_M

Excellent

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

Global Score
76 vs 89
Hardware Fit
45 vs 85
Quality Score
89 vs 91

Hardware

Gemma4-31B:31B qwen3.6-27b-mtp
MachineGMKtec NucBox EVO-T2SASUS
CPUIntel Core™ Ultra X7 358HAMD Ryzen 7 7800X3D 8-Core Processor
Cores1616
RAM64 GB31 GB
GPUIntel(R) Arc(TM) B390 GPUNVIDIA GeForce RTX 4090, Raphael
OSMicrosoft Windows 11 Pro 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedperformance

Performance

Gemma4-31B:31B qwen3.6-27b-mtp
Tokens/sec3.874.9
First chunk3536 ms3 ms
TTFT3.5 s235 ms
Load time19.6 sN/A
Memory usage19.9 GB21.5 GB
Memory %31%70%

HW Fit Score Breakdown

Gemma4-31B:31B

Speed
5/50
TTFT
10/20
Memory
30/30

qwen3.6-27b-mtp

Speed
50/50
TTFT
20/20
Memory
15/30

Quality

Gemma4-31B:31B

Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.6-27b-mtp

Reasoning
18/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View Gemma4-31B:31B details | View qwen3.6-27b-mtp 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