qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Core™ i9-14900K
gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jun 26, 2026 · Cortex-X925
Global Score
83 vs 86
Hardware Fit
70 vs 78
Quality Score
89 vs 90
Hardware
qwen3:30b-a3b-inst… gemma4:12b
MachineMicro-Star International Co., Ltd. MS-7D98NVIDIA NVIDIA_DGX_Spark
CPUIntel Core™ i9-14900KCortex-X925
Cores3220
RAM128 GB122 GB
GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Device 2e12
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64arm64
Power Modebalancedperformance
Performance
qwen3:30b-a3b-inst… gemma4:12b
Tokens/sec21.026.3
First chunk473 ms545 ms
TTFT473 ms545 ms
Load time8.6 s9.5 s
Memory usage17.7 GB8.4 GB
Memory %14%7%
HW Fit Score Breakdown
qwen3:30b-a3b-instruct-…
Speed
20/50
TTFT
20/20
Memory
30/30
gemma4:12b
Speed
28/50
TTFT
20/20
Memory
30/30
Quality
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
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