OR

Ornith 1.0 35B FP8 BLOCK MTP

OrnithGGUF by mradermacherUpdated 2026-10-24
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant13.2 GB
Quick answer

Ornith 1.0 35B FP8 BLOCK MTP needs about 22.9 GB of memory at Q4_K_M (a 21.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 13.2 GB (Q2_K) to 37.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Ornith 1.0 35B FP8 BLOCK MTP – a large‑scale MTP‑enabled LLM

Ornith 1.0 35B FP8 BLOCK MTP is a 35.5 billion‑parameter model with a Qwen3.6 MTP head grafted onto an FP8_BLOCK base. It supports coding, reasoning, tools, and vision. The model is released under the MIT license.

Good at

  • Coding
  • Reasoning
  • Vision

Limits

  • Requires 262144 context tokens
  • No private training corpus
  • No dedicated vision hardware

Best for

  • Code generation
  • Complex reasoning tasks
  • Multimodal content analysis

Who it’s for. Developers and researchers needing a large, versatile LLM with MTP throughput. The model is suitable for local deployment via llama.cpp or vLLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.2 GB 14.4 GB
Too big Get file →
Q3_K_S15.5 GB 16.7 GB
Too big Get file →
Q3_K_M17.2 GB 18.4 GB
Too big Get file →
Q3_K_L18.6 GB 19.7 GB
Too big Get file →
IQ4_XS19.4 GB 20.6 GB
Too big Get file →
Q4_K_S20.4 GB 21.6 GB
Too big Get file →
Q4_K_M21.7 GB 22.9 GB
Too big Get file →
Q5_K_S24.6 GB 25.8 GB
Too big Get file →
Q5_K_M25.3 GB 26.5 GB
Too big Get file →
Q6_K29.2 GB 30.4 GB
Too big Get file →
Q8_037.8 GB 39.0 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (13.25 GB, 14.4 GB memory). For 16 GB VRAM, Q4_K_M (21.71 GB, 22.9 GB memory) is a good balance. For 32 GB VRAM, Q6_K (29.21 GB, 30.4 GB memory) provides higher quality.

What GPU do you need for Ornith 1.0 35B FP8 BLOCK 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: the best quant that fits is Q2_K (13.2 GB file, about 14.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.7 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (29.2 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.8 GB file, about 39.0 GB in use).

Which Ornith 1.0 35B FP8 BLOCK MTP quant should you choose?

Q4_K_M is the usual starting point for Ornith 1.0 35B FP8 BLOCK MTP: it balances file size and quality well. Here it is a 21.7 GB file.

The Q8_0 file is 37.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 13.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 bymradermacher
FamilyOrnith
Licensemit
Downloads (HF)683
Last updated2026-10-24

Frequently asked questions about Ornith 1.0 35B FP8 BLOCK MTP

How much VRAM does Ornith 1.0 35B FP8 BLOCK MTP need?

About 22.9 GB at Q4_K_M with an 8K context window. That is the 21.7 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 FP8 BLOCK MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ornith 1.0 35B FP8 BLOCK MTP GGUF?

It depends on the quant: Q2_K is 13.2 GB, Q3_K_S is 15.5 GB, Q3_K_M is 17.2 GB, Q3_K_L is 18.6 GB, IQ4_XS is 19.4 GB, Q4_K_S is 20.4 GB and 5 more.

What context length does Ornith 1.0 35B FP8 BLOCK 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 FP8 BLOCK MTP GGUF?

The files are on Hugging Face in the mradermacher/Ornith-1.0-35B-FP8-BLOCK-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 FP8 BLOCK 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 FP8 BLOCK MTP on 8 GB VRAM?

The Q2_K quant requires 13.25 GB file size and estimates 14.4 GB VRAM at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

Yes, the model has detected vision abilities and includes vision tensors.

Is the model trained on private data?

No, the model is a direct MTP graft with no private training corpus.

Other GGUFs of Ornith-1.0-35B-FP8-BLOCK-MTP

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ornith models

All Ornith →

Other large models

All large models →