Back to leaderboard

hf.co/Edge-Quant/Nanbeige4.1-3B-Q8_0-GGUF:Q8_0

OLLAMA GGUF

llama · 3.93B · unknown

Not Rec.

Aug 22, 2026 · Apple M1 Pro

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

Global Score
52 vs 66
Hardware Fit
75 vs 23
Quality Score
42 vs 84

Hardware

hf.co/Edge-Quant/N… GPT-120B:120b
MachineMacBook ProHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M1 ProNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1020
RAM16 GB55 GB
GPUApple M1 ProNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 26.6.2Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/Edge-Quant/N… GPT-120B:120b
Tokens/sec43.516.8
First chunk225 ms11247 ms
TTFT30.0 s12.2 s
Load time2.7 s77.3 s
Memory usage8.2 GB61.6 GB
Memory %51%113%

HW Fit Score Breakdown

hf.co/Edge-Quant/Nanbei…

Speed
50/50
TTFT
0/20
Memory
25/30

GPT-120B:120b

Speed
21/50
TTFT
2/20
Memory
0/30

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

GPT-120B:120b

Reasoning
16/20
Coding
19/20
Instruction
11/20
Structured
13/15
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
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest