Back to leaderboard

Qwen3-Next-80B:80B

OLLAMA GGUF

qwen3next · 79.7B · unknown

Not Rec.

Aug 18, 2026 · Intel Core™ i7-14700F

qwen3.6:35b-a3b-q8_0

OLLAMA GGUF

qwen35moe · 36.0B · Q8_0

Not Rec.

Jul 7, 2026 · Cortex-X925

Global Score
25 vs 80
Hardware Fit
71 vs 79
Quality Score
5 vs 81

Hardware

Qwen3-Next-80B:80B qwen3.6:35b-a3b-q8_0
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCASUSTeK COMPUTER INC. GX10
CPUIntel Core™ i7-14700FCortex-X925
Cores2820
RAM128 GB122 GB
GPUNVIDIA GeForce RTX 5080Device 2e12
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance

Performance

Qwen3-Next-80B:80B qwen3.6:35b-a3b-q8_0
Tokens/sec29.155.5
First chunk815 ms528 ms
TTFT769 ms30.0 s
Load time56.9 s32.6 s
Memory usage61.7 GB41.0 GB
Memory %48%34%

HW Fit Score Breakdown

Qwen3-Next-80B:80B

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

qwen3.6:35b-a3b-q8_0

Speed
50/50
TTFT
0/20
Memory
29/30

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

qwen3.6:35b-a3b-q8_0

Reasoning
18/20
Coding
13/20
Instruction
17/20
Structured
10/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Adequate 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