gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor
deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Global Score
87 vs 37
Hardware Fit
75 vs 73
Quality Score
92 vs 22
Hardware
gemma4:latest deepseek-r1:1.5b
MachineMicro-Star International Co., Ltd. MS-7E47LENOVO 20L7CTO1WW
CPUAMD Ryzen 9 9950X 16-Core ProcessorIntel Core™ i5-8350U
Cores328
RAM125 GB23 GB
GPUAMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPERKaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Pro 10.0.26100Fedora Linux 43
Archx64x64
Power Modebalancedlow-power
Performance
gemma4:latest deepseek-r1:1.5b
Tokens/sec42.418.4
First chunk472 ms593 ms
TTFT3.8 s30.0 s
Load time0.3 s3.8 s
Memory usage12.3 GB1.0 GB
Memory %10%4%
HW Fit Score Breakdown
gemma4:latest
Speed
40/50
TTFT
5/20
Memory
30/30
deepseek-r1:1.5b
Speed
43/50
TTFT
0/20
Memory
30/30
Quality
gemma4:latest
Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
deepseek-r1:1.5b
Reasoning
4/20
Coding
0/20
Instruction
5/20
Structured
3/15
Math
7/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Weak
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