gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
qwen3.8:latest
OLLAMA GGUFqwen35 · 27.3B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
76 vs 68
Hardware Fit
82 vs 22
Quality Score
73 vs 88
Hardware
gemma4:e2b qwen3.8:latest
MachineLENOVO 20U30029MBSystem manufacturer
CPUIntel Core™ i5-10210UAMD Ryzen 9 5950X 16-Core Processor
Cores832
RAM15 GB32 GB
GPUCometLake-U GT2 [UHD Graphics]NVIDIA GeForce RTX 3090
OSPop 24.04 LTSMicrosoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modeperformancebalanced
Performance
gemma4:e2b qwen3.8:latest
Tokens/sec13.510.0
First chunk1270 ms1041 ms
TTFT1.3 s14.3 s
Load time13.4 s22.3 s
Memory usage6.5 GB26.2 GB
Memory %42%82%
HW Fit Score Breakdown
gemma4:e2b
Speed
35/50
TTFT
20/20
Memory
27/30
qwen3.8:latest
Speed
12/50
TTFT
1/20
Memory
9/30
Quality
gemma4:e2b
Reasoning
10/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
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
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