Qwen3-0.6B vs tiny-mixtral

Specs, VRAM requirements and download trends — updated 6 August 2026.

Qwen · A
Params
750 M
Context
40,960
30d
29.7 M
apache-2.0 · commercial OK
TitanML · B
Params
250 M
Context
131,072
30d
490 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-0.6B tiny-mixtral
Parameters 750 M 250 M
Architecture Qwen3ForCausalLM MixtralForCausalLM
Context length 40,960 131,072
Licence apache-2.0
Commercial use Allowed Unknown
Languages
Downloads 30d 29,699,637 489,554
Downloads all time 180.6 M 2.7 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2024-04-24

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

29.7 M470 K
Qwen3-0.6B tiny-mixtral

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

tiny-mixtral · fp16 @ 128K ctx 2.2 GB / 24 GB
✅ Runs comfortably
Qwen3-0.6B · fp16 2.3 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons