tinyllama
OLLAMA GGUFMar 6, 2026 · Apple M4
qwen3.5:9b
OLLAMA GGUFqwen35 · 9.7B · Q4_K_M
Mar 5, 2026 · AMD RYZEN AI MAX+ 395
Global Score
43 vs 57
Hardware Fit
100 vs 61
Quality Score
19 vs 55
Hardware
tinyllama qwen3.5:9b
MachineMacBook AirAZW GTR Pro
CPUApple M4AMD RYZEN AI MAX+ 395
Cores1032
RAM32 GB125 GB
GPUApple M4AMD Radeon 8060S
OSmacOS 26.3Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power
Performance
tinyllama qwen3.5:9b
Tokens/sec133.430.3
First chunk61 ms205 ms
TTFT61 ms8.7 s
Load time0.5 s5.6 s
Memory usage0.2 GB18.8 GB
Memory %1%15%
HW Fit Score Breakdown
tinyllama
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5:9b
Speed
30/50
TTFT
1/20
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
qwen3.5:9b
Reasoning
17/20
Coding
2/20
Instruction
7/20
Structured
8/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate 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