qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
qwen2.5:72b
OLLAMA GGUFqwen2 · 72.7B · Q4_K_M
Jun 27, 2026 · Cortex-X925
Global Score
68 vs 75
Hardware Fit
22 vs 50
Quality Score
88 vs 86
Hardware
qwen3.8:latest qwen2.5:72b
MachineSystem manufacturerNVIDIA NVIDIA_DGX_Spark
CPUAMD Ryzen 9 5950X 16-Core ProcessorCortex-X925
Cores3220
RAM32 GB122 GB
GPUNVIDIA GeForce RTX 3090Device 2e12
OSMicrosoft Windows 11 Pro 10.0.26300Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
qwen3.8:latest qwen2.5:72b
Tokens/sec10.04.4
First chunk1041 ms529 ms
TTFT14.3 s529 ms
Load time22.3 s49.7 s
Memory usage26.2 GB54.0 GB
Memory %82%44%
HW Fit Score Breakdown
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
qwen2.5:72b
Speed
4/50
TTFT
20/20
Memory
26/30
Quality
qwen3.8:latest
Reasoning
19/20
Coding
19/20
Instruction
10/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen2.5:72b
Reasoning
19/20
Coding
19/20
Instruction
12/20
Structured
14/15
Math
12/15
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