gemma4:12b
OLLAMA GGUFgemma4 · 11.9B · Q4_K_M
Nov 13, 2026 · Intel Gen Intel® Core™ i7-12700
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
86 vs 72
Hardware Fit
80 vs 77
Quality Score
89 vs 70
Hardware
gemma4:12b llama3.1:8b
MachineASUSMacBook Pro
CPUIntel Gen Intel® Core™ i7-12700Apple M1 Pro
Cores2010
RAM30 GB16 GB
GPUAlder Lake-S GT1 [UHD Graphics 770], NVIDIA GeForce RTX 3060Apple M1 Pro
OSUbuntu 26.04.1 LTSmacOS 26.6.2
Archx64arm64
Power Modelow-powerbalanced
Performance
gemma4:12b llama3.1:8b
Tokens/sec74.421.5
First chunk152 ms368 ms
TTFT30.0 s368 ms
Load time0.0 s6.9 s
Memory usage0.8 GB12.9 GB
Memory %3%81%
HW Fit Score Breakdown
gemma4:12b
Speed
50/50
TTFT
0/20
Memory
30/30
llama3.1:8b
Speed
47/50
TTFT
20/20
Memory
10/30
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
llama3.1:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
4/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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