Back to leaderboard

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Good

Aug 24, 2026 · Intel Core™ Ultra X7 358H

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
78 vs 62
Hardware Fit
59 vs 35
Quality Score
86 vs 73

Hardware

GPT-20B:20b qwen3.5-4b-mlx
MachineGMKtec NucBox EVO-T2SMac mini
CPUIntel Core™ Ultra X7 358HApple M4 Pro
Cores1614
RAM64 GB64 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

GPT-20B:20b qwen3.5-4b-mlx
Tokens/sec19.60.0
First chunk2068 ms5548 ms
TTFT9.9 s5.5 s
Load time12.8 sN/A
Memory usage12.9 GB2.9 GB
Memory %20%5%

HW Fit Score Breakdown

GPT-20B:20b

Speed
26/50
TTFT
3/20
Memory
30/30

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

Quality

GPT-20B:20b

Reasoning
18/20
Coding
18/20
Instruction
11/20
Structured
14/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate 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