gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Aug 22, 2026 · Apple M1 Pro
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
63 vs 78
Hardware Fit
62 vs 49
Quality Score
63 vs 91
Hardware
gemma4:12b qwen3-next:80b-a3b…
MachineMacBook ProDell Inc. Precision Tower 7910
CPUApple M1 ProIntel Xeon® E5-2637 v3
Cores1016
RAM16 GB96 GB
GPUApple M1 ProNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSmacOS 26.6.2Microsoft Windows 10 Pro 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
gemma4:12b qwen3-next:80b-a3b…
Tokens/sec15.38.7
First chunk1142 ms1524 ms
TTFT30.0 s1.5 s
Load time5.4 s63.9 s
Memory usage7.6 GB48.3 GB
Memory %47%50%
HW Fit Score Breakdown
gemma4:12b
Speed
36/50
TTFT
0/20
Memory
26/30
qwen3-next:80b-a3b-inst…
Speed
9/50
TTFT
15/20
Memory
25/30
Quality
gemma4:12b
Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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