Gemma4-31B:31B
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Aug 18, 2026 · Intel Core™ Ultra X7 358H
llama3.3:70b
OLLAMA GGUFllama · 70.6B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
76 vs 73
Hardware Fit
45 vs 51
Quality Score
89 vs 83
Hardware
Gemma4-31B:31B llama3.3:70b
MachineGMKtec NucBox EVO-T2SNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ Ultra X7 358HCortex-X925
Cores1620
RAM64 GB122 GB
GPUIntel(R) Arc(TM) B390 GPUDevice 2e12
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
Gemma4-31B:31B llama3.3:70b
Tokens/sec3.84.6
First chunk3536 ms560 ms
TTFT3.5 s560 ms
Load time19.6 s13.8 s
Memory usage19.9 GB49.5 GB
Memory %31%41%
HW Fit Score Breakdown
Gemma4-31B:31B
Speed
5/50
TTFT
10/20
Memory
30/30
llama3.3:70b
Speed
4/50
TTFT
20/20
Memory
27/30
Quality
Gemma4-31B:31B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
14/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
llama3.3:70b
Reasoning
17/20
Coding
18/20
Instruction
12/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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