qwen3.8:27b
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 3, 2026 · Cortex-X925
gpt-oss:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Oct 2, 2026 · Cortex-X925
Global Score
84 vs 83
Hardware Fit
66 vs 64
Quality Score
92 vs 91
Hardware
qwen3.8:27b gpt-oss:120b
MachineNVIDIA NVIDIA_DGX_SparkNVIDIA NVIDIA_DGX_Spark
CPUCortex-X925Cortex-X925
Cores2020
RAM122 GB122 GB
GPUDevice 2e12Device 2e12
OSUbuntu 24.04.5 LTSUbuntu 24.04.5 LTS
Archarm64arm64
Power Modeperformanceperformance
Performance
qwen3.8:27b gpt-oss:120b
Tokens/sec29.428.6
First chunk306 ms422 ms
TTFT4.8 s2.5 s
Load time5.3 s9.9 s
Memory usage16.2 GB60.1 GB
Memory %13%49%
HW Fit Score Breakdown
qwen3.8:27b
Speed
31/50
TTFT
5/20
Memory
30/30
gpt-oss:120b
Speed
30/50
TTFT
9/20
Memory
25/30
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:120b
Reasoning
19/20
Coding
19/20
Instruction
14/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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