qwen3.8:27b-bf16
OLLAMA GGUFqwen35 · 27.3B · BF16
Aug 22, 2026 · AMD EPYC 7713 64-Core Processor
ornith-1.5-35b
LM-STUDIO GGUFqwen35moe · 35B · Q4_K_M
Aug 21, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
85 vs 85
Hardware Fit
77 vs 88
Quality Score
88 vs 84
Hardware
qwen3.8:27b-bf16 ornith-1.5-35b
MachineDell Inc. PowerEdge XE8545Micro-Star International Co., Ltd. MS-7E51
CPUAMD EPYC 7713 64-Core ProcessorAMD Ryzen 7 9700X 8-Core Processor
Cores12816
RAM1007 GB31 GB
GPUGA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB], Integrated Matrox G200eW3 Graphics Controller, GA100 [A100 SXM4 80GB], GA100 [A100 SXM4 80GB]NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSRocky Linux 8.10Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeunknownbalanced
Performance
qwen3.8:27b-bf16 ornith-1.5-35b
Tokens/sec27.280.4
First chunk237 ms24 ms
TTFT237 ms231 ms
Load time43.8 sN/A
Memory usage68.8 GB20.2 GB
Memory %7%65%
HW Fit Score Breakdown
qwen3.8:27b-bf16
Speed
27/50
TTFT
20/20
Memory
30/30
ornith-1.5-35b
Speed
50/50
TTFT
20/20
Memory
18/30
Quality
qwen3.8:27b-bf16
Reasoning
18/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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