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-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
25 vs 80
Hardware Fit
71 vs 77
Quality Score
5 vs 81

Hardware

Qwen3-Next-80B:80B qwen3.6:35b-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M5 Max
Cores2818
RAM128 GB48 GB
GPUNVIDIA GeForce RTX 5080Apple M5 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3-Next-80B:80B qwen3.6:35b-mlx
Tokens/sec29.1129.8
First chunk815 ms77 ms
TTFT769 ms30.0 s
Load time56.9 s1.8 s
Memory usage61.7 GB19.7 GB
Memory %48%41%

HW Fit Score Breakdown

Qwen3-Next-80B:80B

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

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

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-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak 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