Qwen3-Next-80B:80B
OLLAMA GGUFqwen3next · 79.7B · unknown
Aug 18, 2026 · Intel Core™ Ultra X7 358H
qwen/qwen3.6-35b-a3b
LM-STUDIO MLXqwen3_5_moe · 35B · 6bit
Jul 17, 2026 · Apple M5 Max
Global Score
19 vs 87
Hardware Fit
52 vs 90
Quality Score
5 vs 86
Hardware
Qwen3-Next-80B:80B qwen/qwen3.6-35b-a3b
MachineGMKtec NucBox EVO-T2SMacBook Pro
CPUIntel Core™ Ultra X7 358HApple M5 Max
Cores1618
RAM64 GB64 GB
GPUIntel(R) Arc(TM) B390 GPUApple M5 Max
OSMicrosoft Windows 11 Pro 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
Qwen3-Next-80B:80B qwen/qwen3.6-35b-a3b
Tokens/sec1000000.086.5
First chunk5563 ms9 ms
TTFT30.0 s175 ms
Load time72.5 sN/A
Memory usage61.3 GB37.9 GB
Memory %97%59%
HW Fit Score Breakdown
Qwen3-Next-80B:80B
Speed
50/50
TTFT
0/20
Memory
2/30
qwen/qwen3.6-35b-a3b
Speed
50/50
TTFT
20/20
Memory
20/30
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
qwen/qwen3.6-35b-a3b
Reasoning
16/20
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest