gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Jul 7, 2026 · Cortex-X925
llama3.2:latest
OLLAMA GGUFllama · 3.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
Global Score
66 vs 76
Hardware Fit
40 vs 100
Quality Score
77 vs 65
Hardware
gemma4:31b llama3.2:latest
MachineASUSTeK COMPUTER INC. GX10Micro-Star International Co., Ltd. MS-7B79
CPUCortex-X925AMD Ryzen 5 2600X Six-Core Processor
Cores2012
RAM122 GB16 GB
GPUDevice 2e12NVIDIA GeForce GTX 1080
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
gemma4:31b llama3.2:latest
Tokens/sec10.757.0
First chunk983 ms264 ms
TTFT20.3 s264 ms
Load time8.8 s9.7 s
Memory usage21.4 GB2.6 GB
Memory %18%16%
HW Fit Score Breakdown
gemma4:31b
Speed
10/50
TTFT
0/20
Memory
30/30
llama3.2:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
gemma4:31b
Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
llama3.2:latest
Reasoning
11/20
Coding
15/20
Instruction
15/20
Structured
12/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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