Qwen3-Next-80B:80B
OLLAMA GGUFqwen3next · 79.7B · unknown
Aug 18, 2026 · Intel Core™ i7-14700F
ornith-1.5-35b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Aug 21, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
25 vs 85
Hardware Fit
71 vs 88
Quality Score
5 vs 84
Hardware
Qwen3-Next-80B:80B ornith-1.5-35b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMicro-Star International Co., Ltd. MS-7E51
CPUIntel Core™ i7-14700FAMD Ryzen 7 9700X 8-Core Processor
Cores2816
RAM128 GB31 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
Qwen3-Next-80B:80B ornith-1.5-35b
Tokens/sec29.180.4
First chunk815 ms24 ms
TTFT769 ms231 ms
Load time56.9 sN/A
Memory usage61.7 GB20.2 GB
Memory %48%65%
HW Fit Score Breakdown
Qwen3-Next-80B:80B
Speed
29/50
TTFT
17/20
Memory
25/30
ornith-1.5-35b
Speed
50/50
TTFT
20/20
Memory
18/30
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
ornith-1.5-35b
Reasoning
14/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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