Qwen3.6-35B-A3B-NVFP4 vs Llama-3_3-Nemotron-Super-49B-v1_5-FP8

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

nvidia · A
Params
18.7 B
Context
30d
11.3 M
apache-2.0 · commercial OK
nvidia · B
Params
49.9 B
Context
131,072
30d
256 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.6-35B-A3B-NVFP4 Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Parameters 18.7 B 49.9 B
Architecture Qwen3_5MoeForConditionalGeneration DeciLMForCausalLM
Context length 131,072
Licence apache-2.0 other
Commercial use Allowed Unknown
Languages 1
Downloads 30d 11,298,952 255,770
Downloads all time 19.7 M 917 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-05-27 2025-07-31

Download trend

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

11.3 M250 K
Qwen3.6-35B-A3B-NVFP4 Llama-3_3-Nemotron-Super-49B-v1_5-FP8

VRAM side by side

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

Qwen3.6-35B-A3B-NVFP4 · fp16 29.1 GB / 24 GB
❌ Won’t fit
Llama-3_3-Nemotron-Super-49B-v1_5-FP8 · fp16 @ 128K ctx 177.4 GB / 24 GB
❌ Won’t fit

Adjacent comparisons