OR

Ornith 1.0 35B NVFP4 MTP

OrnithGGUF by s-batmanUpdated 2026-06-29
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant20.3 GB
Quick answer

Ornith 1.0 35B NVFP4 MTP needs about 21.5 GB of memory at MXFP4_MOE (a 20.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 20.3 GB (MXFP4_MOE) to 21.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Ornith 1.0 35B NVFP4 MTP – a 35B MoE model for efficient single‑GPU inference

Ornith 1.0 35B NVFP4 MTP is a 35.5B‑parameter Qwen3.5 MoE model quantized with NVFP4 and MTP heads. It is designed for NVIDIA Blackwell GPUs and supports a 262144‑token context window. The model is MIT licensed and emits a reasoning_content block before final answers.

Good at

  • Reasoning tasks
  • Agentic coding
  • Large context handling

Limits

  • No vision support
  • Requires Blackwell GPU for optimal performance
  • Large VRAM needed for full model

Best for

  • Coding agent development
  • Large‑context reasoning
  • Single‑GPU deployment

Who it’s for. Developers building agentic coding assistants who need a large‑parameter MoE model that runs on a single NVIDIA Blackwell GPU. The model is suitable for users who can allocate the required VRAM and want to leverage MTP speculative decoding.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE20.3 GB 21.5 GB
Too big Get file →
—21.3 GB 22.5 GB
Too big Get file →

For 8 GB VRAM, use the MXFP4_MOE quantization (20.3 GB file, ~21.5 GB memory at 8 k context). For 12 GB VRAM, the NVFP4_MTP quantization (21.31 GB file, ~22.5 GB memory at 8 k context) is recommended. Memory estimates are approximate.

What GPU do you need for Ornith 1.0 35B NVFP4 MTP?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is the main file (21.3 GB file, about 22.5 GB in use).

Which Ornith 1.0 35B NVFP4 MTP quant should you choose?

MXFP4_MOE (20.3 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized bys-batman
FamilyOrnith
Licensemit
Downloads (HF)2,124
Last updated2026-06-29

Frequently asked questions about Ornith 1.0 35B NVFP4 MTP

How much VRAM does Ornith 1.0 35B NVFP4 MTP need?

About 21.5 GB at MXFP4_MOE with an 8K context window. That is the 20.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Ornith 1.0 35B NVFP4 MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ornith 1.0 35B NVFP4 MTP GGUF?

It depends on the quant: MXFP4_MOE is 20.3 GB, file is 21.3 GB.

What context length does Ornith 1.0 35B NVFP4 MTP support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.

Where can I download Ornith 1.0 35B NVFP4 MTP GGUF?

The files are on Hugging Face in the s-batman/Ornith-1.0-35B-NVFP4-MTP-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Ornith 1.0 35B NVFP4 MTP use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Ornith 1.0 35B on 8 GB VRAM?

The MXFP4_MOE quantization requires about 21.5 GB VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision?

No, the GGUF does not include a vision tower.

What license applies to this model?

The model is MIT licensed.

Other GGUFs of Ornith-1.0-35B

Similar models

Browse all →

More from s-batman

All by s-batman →

More Ornith models

All Ornith →

Other large models

All large models →