Back to leaderboard

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

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

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
93 vs 97
Hardware Fit
91 vs 95
Quality Score
94 vs 98

Hardware

GPT-20B:20b qwen3-30b-a3b-thin…
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMac Studio
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M2 Max
Cores2012
RAM55 GB96 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUApple M2 Max
OSMicrosoft Windows 11 Pro 10.0.28000macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

GPT-20B:20b qwen3-30b-a3b-thin…
Tokens/sec57.879.6
First chunk203 ms11 ms
TTFT3.0 s1.7 s
Load time19.2 s7.1 s
Memory usage12.0 GB0.0 GB
Memory %22%0%

HW Fit Score Breakdown

GPT-20B:20b

Speed
50/50
TTFT
11/20
Memory
30/30

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
15/20
Memory
30/30

Quality

GPT-20B:20b

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

qwen3-30b-a3b-thinking-…

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