gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Jun 26, 2026 · Cortex-X925
qwen3:30b-a3b-instruct-2507-q4_K_M
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jul 31, 2026 · Intel Core™ i9-14900K
Global Score
86 vs 83
Hardware Fit
78 vs 70
Quality Score
90 vs 89
Hardware
gemma4:12b qwen3:30b-a3b-inst…
MachineNVIDIA NVIDIA_DGX_SparkMicro-Star International Co., Ltd. MS-7D98
CPUCortex-X925Intel Core™ i9-14900K
Cores2032
RAM122 GB128 GB
GPUDevice 2e12Intel(R) UHD Graphics 770, NVIDIA Quadro K4000
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modeperformancebalanced
Performance
gemma4:12b qwen3:30b-a3b-inst…
Tokens/sec26.321.0
First chunk545 ms473 ms
TTFT545 ms473 ms
Load time9.5 s8.6 s
Memory usage8.4 GB17.7 GB
Memory %7%14%
HW Fit Score Breakdown
gemma4:12b
Speed
28/50
TTFT
20/20
Memory
30/30
qwen3:30b-a3b-instruct-…
Speed
20/50
TTFT
20/20
Memory
30/30
Quality
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
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