Back to leaderboard

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score
90 vs 71
Hardware Fit
79 vs 88
Quality Score
94 vs 63

Hardware

GPT-20B:20b qwen3.5-4b-mlx
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxMacBook Air
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorApple M4
Cores3210
RAM31 GB32 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUApple M4
OSMicrosoft Windows 11 Home 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced

Performance

GPT-20B:20b qwen3.5-4b-mlx
Tokens/sec36.623.1
First chunk722 ms3279 ms
TTFT4.7 s3.3 s
Load time0.3 sN/A
Memory usage13.1 GB2.9 GB
Memory %42%9%

HW Fit Score Breakdown

GPT-20B:20b

Speed
46/50
TTFT
6/20
Memory
27/30

qwen3.5-4b-mlx

Speed
45/50
TTFT
13/20
Memory
30/30

Quality

GPT-20B:20b

Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

qwen3.5-4b-mlx

Reasoning
15/20
Coding
16/20
Instruction
6/20
Structured
6/15
Math
11/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Weak Structured Output: Weak Math: Adequate 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