OR

Ornstein3.6 27B MTP NSC ACE SABER

OrnsteinGGUF by GestaltLabsUpdated 2026-05-14
Download on Hugging Face
Parameters461M
Context256K
Layers65
Architectureqwen35
Smallest quant10.9 GB
Quick answer

Ornstein3.6 27B MTP NSC ACE SABER needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.9 GB (Q2_K) to 54.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Ornstein3.6 27B MTP NSC ACE SABER – a multimodal Qwen3.5/3.6 GGUF model

This model is a 27B parameter Qwen3.5/3.6 checkpoint quantized to GGUF. It supports tools and vision, and includes MTP capability. The context length is 262144 tokens.

Good at

  • Vision and text multimodal tasks
  • Tool usage
  • MTP inference

Limits

  • No external vision support beyond the provided encoder
  • Requires a llama.cpp build with Qwen3.5/Qwen3.6 MTP support
  • License is apache-2.0

Best for

  • Multimodal content generation
  • Automated tool integration
  • Large context reasoning

Who it’s for. Developers building multimodal applications that need a large context window and tool use. Researchers testing MTP and vision capabilities in a GGUF format.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.9 GB 13.5 GB
Too big Get file →
Q3_K_S12.3 GB 14.9 GB
Too big Get file →
Q3_K_M13.5 GB 16.2 GB
Too big Get file →
Q3_K_L14.6 GB 17.2 GB
Too big Get file →
Q4_K_S15.8 GB 18.5 GB
Too big Get file →
Q4_K_M16.8 GB 19.5 GB
Too big Get file →
Q5_K_S19.0 GB 21.7 GB
Too big Get file →
Q5_K_M19.5 GB 22.2 GB
Too big Get file →
Q6_K22.4 GB 25.1 GB
Too big Get file →
Q8_029.0 GB 31.7 GB
Too big Get file →
F1654.7 GB 57.3 GB
Too big Get file →

For 8 GB VRAM use Q2_K (file size 10.86 GB, estimated 13.5 GB memory). For 12 GB VRAM use Q3_K_S (12.26 GB, 14.9 GB). For 16 GB VRAM use Q4_K_M (16.81 GB, 19.5 GB).

What GPU do you need for Ornstein3.6 27B MTP NSC ACE SABER?

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 Q3_K_S (12.3 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 22.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).

Which Ornstein3.6 27B MTP NSC ACE SABER quant should you choose?

Q4_K_M is the usual starting point for Ornstein3.6 27B MTP NSC ACE SABER: it balances file size and quality well. Here it is a 16.8 GB file.

The Q8_0 file is 29.0 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 10.9 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

Architectureqwen35
Parameters461M
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized byGestaltLabs
FamilyOrnstein
Licenseapache-2.0
Downloads (HF)737
Last updated2026-05-14

Frequently asked questions about Ornstein3.6 27B MTP NSC ACE SABER

How much VRAM does Ornstein3.6 27B MTP NSC ACE SABER need?

About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Ornstein3.6 27B MTP NSC ACE SABER on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ornstein3.6 27B MTP NSC ACE SABER GGUF?

It depends on the quant: Q2_K is 10.9 GB, Q3_K_S is 12.3 GB, Q3_K_M is 13.5 GB, Q3_K_L is 14.6 GB, Q4_K_S is 15.8 GB, Q4_K_M is 16.8 GB and 5 more.

What context length does Ornstein3.6 27B MTP NSC ACE SABER support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download Ornstein3.6 27B MTP NSC ACE SABER GGUF?

The files are on Hugging Face in the GestaltLabs/Ornstein3.6-27B-MTP-NSC-ACE-SABER-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 Ornstein3.6 27B MTP NSC ACE SABER use?

Hugging Face lists the license as apache-2.0. 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?

Yes, the Q2_K quant requires about 13.5 GB memory at 8k context, which fits within 8 GB VRAM with efficient batching.

Does it support vision tasks?

Yes, use the mmproj-Ornstein3.6-27B-MTP-NSC-ACE-SABER-F16.gguf with a llama.cpp multimodal build.

What is MTP support?

MTP (Multi-Task Prompting) is enabled; use --spec-type mtp with a compatible llama.cpp build.

Other GGUFs of Ornstein3.6-27B-MTP-NSC-ACE-SABER

Similar models

Browse all →

More from GestaltLabs

All by GestaltLabs →

More Ornstein models

All Ornstein →

Other tiny models

All tiny models →