gemma4:e2b
OLLAMA GGUFgemma4 · 5.1B · Q4_K_M
Apr 4, 2026 · AMD RYZEN AI MAX+ 395
qwen/qwen3-coder-30b
LM-STUDIO GGUFqwen3moe · 30B · Q4_K_M
Jul 5, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
83 vs 88
Hardware Fit
100 vs 84
Quality Score
76 vs 89
Hardware
gemma4:e2b qwen/qwen3-coder-30b
MachineAZW GTR ProASUS
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 7 7800X3D 8-Core Processor
Cores3216
RAM125 GB31 GB
GPURadeon 8060SNVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.4 LTScachyos rolling
Archx64x64
Power Modeperformanceperformance
Performance
gemma4:e2b qwen/qwen3-coder-30b
Tokens/sec87.995.4
First chunk196 ms11 ms
TTFT196 ms179 ms
Load time2.7 sN/A
Memory usage11.2 GB22.2 GB
Memory %9%73%
HW Fit Score Breakdown
gemma4:e2b
Speed
50/50
TTFT
20/20
Memory
30/30
qwen/qwen3-coder-30b
Speed
50/50
TTFT
20/20
Memory
14/30
Quality
gemma4:e2b
Reasoning
12/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
qwen/qwen3-coder-30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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