llama-3.1-8b-instruct
LM-STUDIO GGUFllama · 8B · Q8_0
Apr 26, 2026 · AMD Ryzen 5 5500
gemma4:12b-it-qat
OLLAMA GGUFgemma4 · 11.9B · Q4_0
Jun 25, 2026 · Apple M4 Pro
Global Score
81 vs 88
Hardware Fit
100 vs 86
Quality Score
73 vs 89
Hardware
llama-3.1-8b-instr… gemma4:12b-it-qat
MachineASUSMac mini
CPUAMD Ryzen 5 5500Apple M4 Pro
Cores1212
RAM31 GB24 GB
GPUNavi 44 [Radeon RX 9060 XT]Apple M4 Pro
OSNobara Linux 43macOS 15.6.1
Archx64arm64
Power Modeperformancebalanced
Performance
llama-3.1-8b-instr… gemma4:12b-it-qat
Tokens/sec35.630.0
First chunk52 ms686 ms
TTFT256 ms7.1 s
Load timeN/A5.4 s
Memory usage8.6 GB7.1 GB
Memory %28%30%
HW Fit Score Breakdown
llama-3.1-8b-instruct
Speed
50/50
TTFT
20/20
Memory
30/30
gemma4:12b-it-qat
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
llama-3.1-8b-instruct
Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
gemma4:12b-it-qat
Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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