tinyllama
OLLAMA GGUFMar 6, 2026 · Apple M4
adityakale/kotakneo
OLLAMA GGUFAug 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
43 vs 77
Hardware Fit
100 vs 100
Quality Score
19 vs 67
Hardware
tinyllama adityakale/kotakneo
MachineMacBook AirAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M4Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
tinyllama adityakale/kotakneo
Tokens/sec133.481.2
First chunk61 ms183 ms
TTFT61 ms183 ms
Load time0.5 s2.5 s
Memory usage0.2 GB17.8 GB
Memory %1%14%
HW Fit Score Breakdown
tinyllama
Speed
50/50
TTFT
20/20
Memory
30/30
adityakale/kotakneo
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
tinyllama
Reasoning
2/20
Coding
2/20
Instruction
7/20
Structured
5/15
Math
0/15
Multilingual
3/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Weak
adityakale/kotakneo
Reasoning
11/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor 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