Qwen3-Next-80B:80B
OLLAMA GGUFqwen3next · 79.7B · unknown
Aug 18, 2026 · Intel Core™ Ultra X7 358H
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
19 vs 65
Hardware Fit
52 vs 96
Quality Score
5 vs 52
Hardware
Qwen3-Next-80B:80B richardyoung/qwyth…
MachineGMKtec NucBox EVO-T2SMac mini
CPUIntel Core™ Ultra X7 358HApple M4 Pro
Cores1612
RAM64 GB24 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
Qwen3-Next-80B:80B richardyoung/qwyth…
Tokens/sec1000000.025.3
First chunk5563 ms397 ms
TTFT30.0 s397 ms
Load time72.5 s6.3 s
Memory usage61.3 GB8.3 GB
Memory %97%34%
HW Fit Score Breakdown
Qwen3-Next-80B:80B
Speed
50/50
TTFT
0/20
Memory
2/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
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
richardyoung/qwythos-9b…
Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
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