qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-14600KF
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
81 vs 86
Hardware Fit
95 vs 78
Quality Score
75 vs 90
Hardware
qwen3:8b gemma4:12b
MachineASUSNVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i5-14600KFCortex-X925
Cores2020
RAM32 GB122 GB
GPUNVIDIA GeForce RTX 4070 Ti SUPERDevice 2e12
OSMicrosoft Windows 11 Famille 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
qwen3:8b gemma4:12b
Tokens/sec108.326.3
First chunk169 ms545 ms
TTFT169 ms545 ms
Load time1.7 s9.5 s
Memory usage5.6 GB8.4 GB
Memory %18%7%
HW Fit Score Breakdown
qwen3:8b
Speed
50/50
TTFT
20/20
Memory
25/30
gemma4:12b
Speed
28/50
TTFT
20/20
Memory
30/30
Quality
qwen3:8b
Reasoning
15/20
Coding
16/20
Instruction
14/20
Structured
14/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma4:12b
Reasoning
18/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
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