tinyllama
OLLAMA GGUFMar 6, 2026 · Apple M4
qwen3.5-0.8b
LM-STUDIO GGUFqwen35 · 0.8B · Q4_K_M
Mar 6, 2026 · Intel Core™ i5-5300U
Global Score
43 vs 48
Hardware Fit
100 vs 61
Quality Score
19 vs 42
Hardware
tinyllama qwen3.5-0.8b
MachineMacBook AirLENOVO 20BUS00700
CPUApple M4Intel Core™ i5-5300U
Cores104
RAM32 GB16 GB
GPUApple M4Intel(R) HD Graphics 5500
OSmacOS 26.3Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
tinyllama qwen3.5-0.8b
Tokens/sec133.46.2
First chunk61 ms4461 ms
TTFT61 ms4.5 s
Load time0.5 sN/A
Memory usage0.2 GB0.7 GB
Memory %1%4%
HW Fit Score Breakdown
tinyllama
Speed
50/50
TTFT
20/20
Memory
30/30
qwen3.5-0.8b
Speed
22/50
TTFT
12/20
Memory
27/30
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
qwen3.5-0.8b
Reasoning
10/20
Coding
2/20
Instruction
10/20
Structured
12/15
Math
2/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate
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