hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0
OLLAMA GGUFllama · 3.93B · unknown
Aug 22, 2026 · Apple M1 Pro
gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Global Score
52 vs 84
Hardware Fit
75 vs 69
Quality Score
42 vs 91
Hardware
hf.co/Edge-Quant/N… gptoss · 20.9B · M…
MachineMacBook ProMac Pro
CPUApple M1 ProIntel Core™ i5-10400
Cores1012
RAM16 GB32 GB
GPUApple M1 ProAMD Radeon RX 6700 XT
OSmacOS 26.6.2macOS 26.5.1
Archarm64x64
Power Modebalancedbalanced
Performance
hf.co/Edge-Quant/N… gptoss · 20.9B · M…
Tokens/sec43.517.5
First chunk225 ms643 ms
TTFT30.0 s7.7 s
Load time2.7 s0.0 s
Memory usage8.2 GB0.8 GB
Memory %51%3%
HW Fit Score Breakdown
hf.co/Edge-Quant/Nanbei…
Speed
50/50
TTFT
0/20
Memory
25/30
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
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
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
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