Ornith-1.5-35B-A3B-NVFP4-Q5K-mtp:latest
OLLAMA GGUFqwen35moe · 35.5B · NVFP4
Aug 23, 2026 · AMD Ryzen 7 9700X 8-Core Processor
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Apr 28, 2026 · Intel Xeon® Gold 6230
Global Score
82 vs 80
Hardware Fit
81 vs 85
Quality Score
82 vs 78
Hardware
Ornith-1.5-35B-A3B… qwen3:8b
MachineMicro-Star International Co., Ltd. MS-7E51HP HP Z8 G4 Workstation
CPUAMD Ryzen 7 9700X 8-Core ProcessorIntel Xeon® Gold 6230
Cores1680
RAM31 GB252 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsTU104GL [Quadro RTX 5000]
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
Ornith-1.5-35B-A3B… qwen3:8b
Tokens/sec67.965.1
First chunk216 ms289 ms
TTFT216 ms4.2 s
Load time12.6 s4.6 s
Memory usage24.1 GB5.6 GB
Memory %78%2%
HW Fit Score Breakdown
Ornith-1.5-35B-A3B-NVFP…
Speed
50/50
TTFT
20/20
Memory
11/30
qwen3:8b
Speed
50/50
TTFT
5/20
Memory
30/30
Quality
Ornith-1.5-35B-A3B-NVFP…
Reasoning
14/20
Coding
19/20
Instruction
15/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen3:8b
Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate 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