gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jun 5, 2026 · AMD Ryzen 7 5800H
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Core™ i9-14900K
Global Score
89 vs 83
Hardware Fit
83 vs 70
Quality Score
92 vs 89
Hardware
gemma4:latest qwen3:30b-a3b-inst…
MachineLENOVO 82JQMicro-Star International Co., Ltd. MS-7D98
CPUAMD Ryzen 7 5800HIntel Core™ i9-14900K
Cores1632
RAM16 GB128 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
gemma4:latest qwen3:30b-a3b-inst…
Tokens/sec46.321.2
First chunk824 ms468 ms
TTFT3.8 s468 ms
Load time21.0 s9.6 s
Memory usage8.9 GB17.7 GB
Memory %56%14%
HW Fit Score Breakdown
gemma4:latest
Speed
50/50
TTFT
11/20
Memory
22/30
qwen3:30b-a3b-instruct-…
Speed
20/50
TTFT
20/20
Memory
30/30
Quality
gemma4:latest
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:30b-a3b-instruct-…
Reasoning
17/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
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