OR

ornith15 35b a3b apex mtp fixed

OrnithGGUF by conFIGur8torUpdated 2026-08-23
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant17.4 GB
Quick answer

ornith15 35b a3b apex mtp fixed needs about 18.6 GB of memory at its main file (a 17.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Ornith-1.5-35B-A3B with repaired MTP head for large‑context LLM tasks

Ornith-1.5-35B-A3B is a 35.5B‑parameter mixture‑of‑experts model based on qwen35moe. It includes a repaired multi‑token‑prediction head that enables speculative decoding. The GGUF export is 17.44 GB and requires about 18.6 GB VRAM at 8 k context.

Good at

  • Large‑context coding
  • Agentic reasoning
  • Speculative decoding

Limits

  • Requires ~18.6 GB VRAM at 8 k context
  • No vision support
  • No quantization options beyond the provided GGUF

Best for

  • Complex coding tasks
  • Agentic workflow automation
  • Fast inference with speculative decoding

Who it’s for. Engineers and researchers who need a large‑context LLM with strong coding and agentic performance. The model is suited for environments that can provide the required VRAM and support llama.cpp or Ollama.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—17.4 GB 18.6 GB
Too big Get file →

The only available quantization is the default GGUF file, 17.44 GB in size. It requires approximately 18.6 GB VRAM at 8 k context. No other quantized variants are provided.

What GPU do you need for ornith15 35b a3b apex mtp fixed?

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 (17.4 GB file, about 18.6 GB in use).

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 byconFIGur8tor
FamilyOrnith
Licensemit
Downloads (HF)1,448
Last updated2026-08-23

Frequently asked questions about ornith15 35b a3b apex mtp fixed

How much VRAM does ornith15 35b a3b apex mtp fixed need?

About 18.6 GB at its main file with an 8K context window. That is the 17.4 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 ornith15 35b a3b apex mtp fixed on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ornith15 35b a3b apex mtp fixed GGUF?

It depends on the quant: file is 17.4 GB.

What context length does ornith15 35b a3b apex mtp fixed 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 ornith15 35b a3b apex mtp fixed GGUF?

The files are on Hugging Face in the conFIGur8tor/ornith15-35b-a3b-apex-mtp-fixed repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ornith15 35b a3b apex mtp fixed 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 this model on 8 GB VRAM?

No, the model needs about 18.6 GB VRAM at 8 k context.

Does the model support speculative decoding?

Yes, the repaired MTP head enables speculative decoding in llama.cpp and Ollama.

Is there vision support?

No, the model does not include vision capabilities.

Other GGUFs of Ornith-1.5-35B-A3B

Similar models

Browse all →

More Ornith models

All Ornith →

Other large models

All large models →