hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0
OLLAMA GGUFllama · 3.93B · unknown
Aug 22, 2026 · Apple M1 Pro
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Aug 15, 2026 · AMD Ryzen 9 3900X 12-Core Processor
Global Score
52 vs 78
Hardware Fit
75 vs 86
Quality Score
42 vs 74
Hardware
hf.co/Edge-Quant/N… qwen3:8b
MachineMacBook Pro—
CPUApple M1 ProAMD Ryzen 9 3900X 12-Core Processor
Cores1024
RAM16 GB64 GB
GPUApple M1 ProNVIDIA GeForce RTX 4060 Ti
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/Edge-Quant/N… qwen3:8b
Tokens/sec43.548.5
First chunk225 ms202 ms
TTFT30.0 s4.3 s
Load time2.7 s4.2 s
Memory usage8.2 GB5.5 GB
Memory %51%9%
HW Fit Score Breakdown
hf.co/Edge-Quant/Nanbei…
Speed
50/50
TTFT
0/20
Memory
25/30
qwen3:8b
Speed
50/50
TTFT
6/20
Memory
30/30
Quality
hf.co/Edge-Quant/Nanbei…
Reasoning
13/20
Coding
1/20
Instruction
7/20
Structured
1/15
Math
13/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate
qwen3:8b
Reasoning
16/20
Coding
8/20
Instruction
14/20
Structured
14/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Weak 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