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 )

qwen3.5-0.8b-mlx

LM-STUDIO MLX

qwen3_5 · 0.8B · 8bit

Good

Mar 3, 2026 · Apple M4

Global Score

66 vs 60

Hardware Fit

23 vs 96

Quality Score

84 vs 44

Hardware

GPT-120B:120b qwen3.5-0.8b-mlx

MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMacBook Air

CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M4

Cores2010

RAM55 GB32 GB

GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUApple M4

OSMicrosoft Windows 11 Pro 10.0.28000macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

GPT-120B:120b qwen3.5-0.8b-mlx

Tokens/sec16.8108.0

First chunk11247 ms2568 ms

TTFT12.2 s2.6 s

Load time77.3 sN/A

Memory usage61.6 GB1.0 GB

Memory %113%3%

HW Fit Score Breakdown

GPT-120B:120b

Speed

21/50

TTFT

2/20

Memory

0/30

qwen3.5-0.8b-mlx

Speed

50/50

TTFT

16/20

Memory

30/30

Quality

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

qwen3.5-0.8b-mlx

Reasoning

10/20

Coding

3/20

Instruction

11/20

Structured

12/15

Math

3/15

Multilingual

5/10

Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

View GPT-120B:120b details | View qwen3.5-0.8b-mlx details

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