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 )

qwen3.5:35b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Good

Mar 7, 2026 · Intel Core™ i5-14600KF

Global Score
93 vs 77
Hardware Fit
91 vs 53
Quality Score
94 vs 87

Hardware

GPT-20B:20b qwen3.5:35b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLASUS
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Intel Core™ i5-14600KF
Cores2020
RAM55 GB32 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUNVIDIA GeForce RTX 4070 Ti SUPER
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

GPT-20B:20b qwen3.5:35b
Tokens/sec57.816.0
First chunk203 ms719 ms
TTFT3.0 s719 ms
Load time19.2 s17.8 s
Memory usage12.0 GB25.0 GB
Memory %22%79%

HW Fit Score Breakdown

GPT-20B:20b

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

qwen3.5:35b

Speed
23/50
TTFT
20/20
Memory
10/30

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

qwen3.5:35b

Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
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