Qwen3.6-35B-A3B-NVFP4 vs JiRackUltra_14b

Specs, VRAM requirements and download trends — updated 21 September 2026.

nvidia · A
Params
18.7 B
Context
30d
8.0 M
apache-2.0 · commercial OK
CMSManhattan · B
Params
14.8 B
Context
131,072
30d
1.0 M
mit · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.6-35B-A3B-NVFP4 JiRackUltra_14b
Parameters 18.7 B 14.8 B
Architecture Qwen3_5MoeForConditionalGeneration Qwen2ForCausalLM
Context length 131,072
Licence apache-2.0 mit
Commercial use Allowed Allowed
Languages 13
Downloads 30d 8,020,372 1,000,579
Downloads all time 34.6 M 1.0 M
Quantizations on the Hub SAFETENSORS GGUF, SAFETENSORS
Gated No No
First seen on the Hub 2026-05-27 2026-08-03

Download trend

Daily snapshots, last 56 days (28 Jul – 21 Sep)

12.6 M229 K
Qwen3.6-35B-A3B-NVFP4 JiRackUltra_14b

VRAM side by side

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

JiRackUltra_14b · Q4_K_M 12.6 GB / 24 GB
✅ Runs comfortably
Qwen3.6-35B-A3B-NVFP4 · fp16 29.1 GB / 24 GB
❌ Won’t fit
JiRackUltra_14b · fp16 @ 128K ctx 68.4 GB / 24 GB
❌ Won’t fit

Adjacent comparisons