qwen3.8:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 3, 2026 · Cortex-X925
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
84 vs 94
Hardware Fit
66 vs 91
Quality Score
92 vs 95
Hardware
qwen3.8:27b gpt-oss:20b
MachineNVIDIA NVIDIA_DGX_SparkFramework Desktop (AMD Ryzen AI Max 300 Series)
CPUCortex-X925AMD RYZEN AI MAX+ 395
Cores2032
RAM122 GB64 GB
GPUDevice 2e12AMD Radeon(TM) 8060S Graphics
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Pro for Workstations 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
qwen3.8:27b gpt-oss:20b
Tokens/sec29.448.0
First chunk306 ms357 ms
TTFT4.8 s2.3 s
Load time5.3 s0.2 s
Memory usage16.2 GB16.4 GB
Memory %13%26%
HW Fit Score Breakdown
qwen3.8:27b
Speed
31/50
TTFT
5/20
Memory
30/30
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
qwen3.8:27b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
gpt-oss:20b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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