llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
Ornith-1.5-35B-A3B-NVFP4-Q5K-mtp:latest
OLLAMA GGUFqwen35moe · 35.5B · NVFP4
Aug 23, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
81 vs 82
Hardware Fit
100 vs 81
Quality Score
73 vs 82
Hardware
llama-3.1-8b-instr… Ornith-1.5-35B-A3B…
MachineASUSMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 5 5500AMD Ryzen 7 9700X 8-Core Processor
Cores1216
RAM31 GB31 GB
GPUNavi 44 [Radeon RX 9060 XT]NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSNobara Linux 43Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modeperformancebalanced
Performance
llama-3.1-8b-instr… Ornith-1.5-35B-A3B…
Tokens/sec35.667.9
First chunk52 ms216 ms
TTFT256 ms216 ms
Load timeN/A12.6 s
Memory usage8.6 GB24.1 GB
Memory %28%78%
HW Fit Score Breakdown
llama-3.1-8b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
Ornith-1.5-35B-A3B-NVFP…
Speed
50/50
TTFT
20/20
Memory
11/30
Quality
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
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
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