gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
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
60 vs 84
Quality Score
93 vs 89
Hardware
gemma4:31b qwen/qwen3-coder-30b
MachineASUSTeK COMPUTER INC. GX10ASUS
CPUCortex-X925AMD Ryzen 7 7800X3D 8-Core Processor
Cores2016
RAM122 GB31 GB
GPUDevice 2e12NVIDIA GeForce RTX 4090, Raphael
OSUbuntu 24.04.4 LTScachyos rolling
Archarm64x64
Power Modeperformanceperformance
Performance
gemma4:31b qwen/qwen3-coder-30b
Tokens/sec10.995.4
First chunk681 ms11 ms
TTFT681 ms179 ms
Load time16.6 sN/A
Memory usage21.4 GB22.2 GB
Memory %18%73%
HW Fit Score Breakdown
gemma4:31b
Speed
10/50
TTFT
20/20
Memory
30/30
qwen/qwen3-coder-30b
Speed
50/50
TTFT
20/20
Memory
14/30
Quality
gemma4:31b
Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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