Back to leaderboard

Qwen3-Next-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · unknown

Not Rec.

Aug 18, 2026 · Intel Core™ i7-14700F

gemma4:12b-it-qat

OLLAMA GGUF

gemma4 · 11.9B · Q4_0

Excellent

Jun 25, 2026 · Apple M4 Pro

Global Score
25 vs 88
Hardware Fit
71 vs 86
Quality Score
5 vs 89

Hardware

Qwen3-Next-80B:80B gemma4:12b-it-qat
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMac mini
CPUIntel Core™ i7-14700FApple M4 Pro
Cores2812
RAM128 GB24 GB
GPUNVIDIA GeForce RTX 5080Apple M4 Pro
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3-Next-80B:80B gemma4:12b-it-qat
Tokens/sec29.130.0
First chunk815 ms686 ms
TTFT769 ms7.1 s
Load time56.9 s5.4 s
Memory usage61.7 GB7.1 GB
Memory %48%30%

HW Fit Score Breakdown

Qwen3-Next-80B:80B

Speed
29/50
TTFT
17/20
Memory
25/30

gemma4:12b-it-qat

Speed
50/50
TTFT
6/20
Memory
30/30

Quality

Qwen3-Next-80B:80B

Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor

gemma4:12b-it-qat

Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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