Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

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
53 vs 66
Hardware Fit
81 vs 23
Quality Score
41 vs 84

Hardware

qwen3.5:4b-mlx GPT-120B:120b
MachineMac miniHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M2NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores820
RAM8 GB55 GB
GPUApple M2NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx GPT-120B:120b
Tokens/sec24.816.8
First chunk317 ms11247 ms
TTFT7.4 s12.2 s
Load time0.0 s77.3 s
Memory usage3.9 GB61.6 GB
Memory %49%113%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
25/30

GPT-120B:120b

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

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

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