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-next-80b-t48:latest

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Not Rec.

Jul 31, 2026 · Intel Xeon® E5-4620 0

Global Score
93 vs 70
Hardware Fit
91 vs 39
Quality Score
94 vs 83

Hardware

GPT-20B:20b qwen3-next-80b-t48…
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLDell Inc. PowerEdge R820
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Intel Xeon® E5-4620 0
Cores2064
RAM55 GB256 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUMicrosoft Remote Display Adapter, Microsoft Basic Display Adapter
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows Server 2022 Datacenter 10.0.20348
Archarm64x64
Power Modebalancedbalanced

Performance

GPT-20B:20b qwen3-next-80b-t48…
Tokens/sec57.83.0
First chunk203 ms3265 ms
TTFT3.0 s3.3 s
Load time19.2 s82.1 s
Memory usage12.0 GB46.9 GB
Memory %22%18%

HW Fit Score Breakdown

GPT-20B:20b

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

qwen3-next-80b-t48:latest

Speed
3/50
TTFT
6/20
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-next-80b-t48:latest

Reasoning
18/20
Coding
18/20
Instruction
9/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Weak 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