qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
gemma4:26b
OLLAMA GGUFgemma4 · 25.2B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
61 vs 84
Hardware Fit
85 vs 80
Quality Score
51 vs 86
Hardware
qwen3:0.6b gemma4:26b
MachineLENOVO 20L7CTO1WWSystem manufacturer
CPUIntel Core™ i5-8350UAMD Ryzen 9 5950X 16-Core Processor
Cores832
RAM23 GB32 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]NVIDIA GeForce RTX 3090
OSFedora Linux 43Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modelow-powerbalanced
Performance
qwen3:0.6b gemma4:26b
Tokens/sec27.0147.6
First chunk597 ms139 ms
TTFT8.7 s30.0 s
Load time1.8 s21.3 s
Memory usage0.9 GB1.7 GB
Memory %4%5%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
gemma4:26b
Speed
50/50
TTFT
0/20
Memory
30/30
Quality
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
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