gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
qwen3-next:80b-a3b-instruct-q4_K_M
OLLAMA GGUFqwen3next · 79.7B · Q4_K_M
Aug 20, 2026 · Intel Xeon® E5-2637 v3
Global Score
86 vs 78
Hardware Fit
80 vs 49
Quality Score
89 vs 91
Hardware
gemma4:12b qwen3-next:80b-a3b…
MachineASUSDell Inc. Precision Tower 7910
CPUIntel Gen Intel® Core™ i7-12700Intel Xeon® E5-2637 v3
Cores2016
RAM30 GB96 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSUbuntu 26.04.1 LTSMicrosoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modelow-powerbalanced
Performance
gemma4:12b qwen3-next:80b-a3b…
Tokens/sec74.48.7
First chunk152 ms1524 ms
TTFT30.0 s1.5 s
Load time0.0 s63.9 s
Memory usage0.8 GB48.3 GB
Memory %3%50%
HW Fit Score Breakdown
gemma4:12b
Speed
50/50
TTFT
0/20
Memory
30/30
qwen3-next:80b-a3b-inst…
Speed
9/50
TTFT
15/20
Memory
25/30
Quality
gemma4:12b
Reasoning
18/20
Coding
15/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-next:80b-a3b-inst…
Reasoning
18/20
Coding
19/20
Instruction
16/20
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