SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

Ornith-1.5-35B-A3B-NVFP4 vs Qwen3.6-35B-A3B-NVFP4

Ornith-1.5-35B-A3B-NVFP4 has 19.5B parameters and Qwen3.6-35B-A3B-NVFP4 has 18.7B parameters; Ornith-1.5-35B-A3B-NVFP4 is released under MIT License and Qwen3.6-35B-A3B-NVFP4 under Apache License 2.0; at 16-bit, Ornith-1.5-35B-A3B-NVFP4 needs about 46.9 GB (1x MI300X from $1.85 an hour) and Qwen3.6-35B-A3B-NVFP4 about 44.8 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field Ornith-1.5-35B-A3B-NVFP4
ornith-ai/Ornith-1.5-35B-A3B-NVFP4
Qwen3.6-35B-A3B-NVFP4
nvidia/Qwen3.6-35B-A3B-NVFP4
Publisher Ornith NVIDIA
Task Text generation Text generation
Modality Text Text
Parameters, as reported 19.5B parameters 18.7B parameters
Architecture Qwen3_5MoeForConditionalGeneration Qwen3_5MoeForConditionalGeneration
Library transformers Model Optimizer
Context length 262,144 tokens 262,144 tokens
Repository size 23.5 GB 23.5 GB
Artifact formats safetensors safetensors
License mit apache-2.0
Access Open weights, no gate Open weights, no gate
Memory at 16-bit (weights and margin) 46.9 GB 44.8 GB
Cheapest GPUs at 16-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Memory at 4-bit (weights and margin) 11.7 GB 11.2 GB
Cheapest GPUs at 4-bit, per hour 1x MI300X, $1.85 1x MI300X, $1.85
Revision viewed 94e431d9cc47 1355db6a0524
Downloads reported by the hub 1.1M 8.4M
Last observed 2026-09-18 2026-09-18

An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.

SAVRN's Notes on Ornith-1.5-35B-A3B-NVFP4

Eight of 256 experts fire on each token. With 19.5B parameters listed, memory comes to 46.9 GB at 16-bit, 23.4 GB at 8-bit, 11.7 GB at 4-bit. All three fit the cheapest setup on our board, one 192 GB MI300X at $1.85 per hour on-demand, leaving the rest of the card to budget for the 262,144 token context. Ornith built it for text generation and trained it through a self-improvement loop that generates its own tasks.

MIT is as light as a license gets: commercial use, modification and redistribution, keeping only the copyright and permission notices. Two things to check. The name says NVFP4 and 35B, yet the 22 files total about 23.5 GB and the 4-bit row reads 9.8 GB of weights, so confirm the precision you are loading. The lineage runs through Ornith-1.0 to Qwen3.5 and Gemma4 with no base-model relation recorded, so confirm the upstream terms yourself.

SAVRN's Notes on Qwen3.6-35B-A3B-NVFP4

NVIDIA's part in this one is the quantization, not the model. It ran Alibaba's Qwen3.6-35B-A3B through Model Optimizer, and its own card says NVIDIA neither owns nor developed the result: 18.7B parameters as a mixture of 256 experts, 8 active per token. Our sizing wants 44.8 GB of memory at 16-bit and 11.2 GB at 4-bit; the cheapest setup we list is one 192 GB MI300X at $1.85 per hour on-demand, and the 262,144 token context is where the rest of that card goes on real jobs.

Before committing, read Alibaba's card for the parent Qwen3.6-35B-A3B, since that is what you are deploying. Apache 2.0 covers commercial use, modification and redistribution, provided the license and NOTICE file stay attached and significant changes are stated. Files were last updated August 29, 2026, three months after the May 27 release, so confirm which revision you pulled.

Questions

Which is larger, Ornith-1.5-35B-A3B-NVFP4 or Qwen3.6-35B-A3B-NVFP4?

Ornith-1.5-35B-A3B-NVFP4 (19.5B parameters) is larger than Qwen3.6-35B-A3B-NVFP4 (18.7B parameters), by the parameter counts their publishers report.

Which is cheaper to run, Ornith-1.5-35B-A3B-NVFP4 or Qwen3.6-35B-A3B-NVFP4?

At 4-bit, Ornith-1.5-35B-A3B-NVFP4 fits on 1x MI300X from $1.85 an hour and Qwen3.6-35B-A3B-NVFP4 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use Ornith-1.5-35B-A3B-NVFP4 commercially?

Yes. Ornith-1.5-35B-A3B-NVFP4 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

Can I use Qwen3.6-35B-A3B-NVFP4 commercially?

Yes. Qwen3.6-35B-A3B-NVFP4 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Related Comparisons