gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K
Global Score
83 vs 80
Hardware Fit
60 vs 60
Quality Score
93 vs 88
Hardware
gemma4:31b qwen3-coder:30b
MachineASUSTeK COMPUTER INC. GX10ASUS
CPUCortex-X925Intel Gen Intel® Core™ i7-12700K
Cores2020
RAM122 GB96 GB
GPUDevice 2e12Parsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
gemma4:31b qwen3-coder:30b
Tokens/sec10.914.7
First chunk681 ms796 ms
TTFT681 ms796 ms
Load time16.6 s0.2 s
Memory usage21.4 GB17.9 GB
Memory %18%19%
HW Fit Score Breakdown
gemma4:31b
Speed
10/50
TTFT
20/20
Memory
30/30
qwen3-coder:30b
Speed
14/50
TTFT
19/20
Memory
27/30
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
qwen3-coder:30b
Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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