Back to leaderboard

qwen3-next:80b-a3b-instruct-q4_K_M

OLLAMA GGUF

qwen3next · 79.7B · Q4_K_M

Good

Aug 18, 2026 · Intel Xeon® E5-2637 v3

GPT-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

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

Global Score
78 vs 87
Hardware Fit
51 vs 81
Quality Score
89 vs 90

Hardware

qwen3-next:80b-a3b… GPT-20B:20b
MachineDell Inc. Precision Tower 7910HP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Xeon® E5-2637 v3AMD Ryzen 9 9955HX3D 16-Core Processor
Cores1632
RAM96 GB31 GB
GPUNVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 10 Pro 10.0.19045Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

qwen3-next:80b-a3b… GPT-20B:20b
Tokens/sec8.736.9
First chunk1251 ms902 ms
TTFT1.3 s4.2 s
Load time61.6 s19.5 s
Memory usage48.3 GB13.1 GB
Memory %50%42%

HW Fit Score Breakdown

qwen3-next:80b-a3b-inst…

Speed
9/50
TTFT
17/20
Memory
25/30

GPT-20B:20b

Speed
47/50
TTFT
7/20
Memory
27/30

Quality

qwen3-next:80b-a3b-inst…

Reasoning
18/20
Coding
19/20
Instruction
14/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

GPT-20B:20b

Reasoning
19/20
Coding
17/20
Instruction
14/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
View qwen3-next:80b-a3b… details | View GPT-20B:20b details

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