qwen2.5-coder:32b
OLLAMA GGUFqwen2 · 32.8B · Q4_K_M
Jun 26, 2026 · Cortex-X925
gemma4:26b
OLLAMA GGUFgemma4 · 25.2B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
78 vs 84
Hardware Fit
59 vs 80
Quality Score
86 vs 86
Hardware
qwen2.5-coder:32b gemma4:26b
MachineNVIDIA NVIDIA_DGX_SparkSystem manufacturer
CPUCortex-X925AMD Ryzen 9 5950X 16-Core Processor
Cores2032
RAM122 GB32 GB
GPUDevice 2e12NVIDIA GeForce RTX 3090
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modeperformancebalanced
Performance
qwen2.5-coder:32b gemma4:26b
Tokens/sec9.5147.6
First chunk394 ms139 ms
TTFT395 ms30.0 s
Load time72.1 s21.3 s
Memory usage26.5 GB1.7 GB
Memory %22%5%
HW Fit Score Breakdown
qwen2.5-coder:32b
Speed
9/50
TTFT
20/20
Memory
30/30
gemma4:26b
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
qwen2.5-coder:32b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
gemma4:26b
Reasoning
17/20
Coding
14/20
Instruction
18/20
Structured
15/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate 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