OR

Ornith 1.5 27B A3B CoderX MTP

OrnithGGUF by ManniX-ITAUpdated 2026-09-16
Download on Hugging Face
Parameters26.2B
Context256K
Layers41
Architectureqwen35moe
Smallest quant0.1 GB
Quick answer

Ornith 1.5 27B A3B CoderX MTP needs about 17.2 GB of memory at Q4_K_M (a 16.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 0.1 GB to 52.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Ornith 1.5 27B A3B CoderX MTP – 26.2B parameter code‑focused model

Ornith 1.5 27B A3B CoderX MTP is a 26.2B parameter model built on the qwen35moe architecture. It is a code‑targeted expert prune of Ornith‑1.5‑35B‑A3B with 184 experts per layer and includes a speculative MTP head. The model supports coding and vision tasks and is released under apache‑2.0.

Good at

  • Coding tasks with high precision
  • Vision‑enabled code generation
  • Large context handling up to 262144 tokens

Limits

  • Requires 8‑k context for memory estimates
  • No fine‑tuning or distillation
  • Only GGUF quantizations available

Best for

  • Developers needing code generation with context
  • Researchers benchmarking code models
  • Users with limited VRAM using lower‑rank quants

Who it’s for. The model is suited for developers and researchers who need a large, code‑focused LLM with vision capabilities and who can run it with GGUF quantizations. It is ideal for those who prefer open‑source models under an apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.3 GB
Fits Get file →
IQ2_XS8.2 GB 9.4 GB
Too big Get file →
IQ2_M9.1 GB 10.2 GB
Too big Get file →
Q2_K_L10.4 GB 11.5 GB
Too big Get file →
Q3_K_S11.5 GB 12.7 GB
Too big Get file →
IQ3_M11.7 GB 12.9 GB
Too big Get file →
Q3_K_M12.7 GB 13.9 GB
Too big Get file →
Q3_K_XL13.2 GB 14.4 GB
Too big Get file →
Q3_K_L13.7 GB 14.9 GB
Too big Get file →
IQ4_XS14.2 GB 15.4 GB
Too big Get file →
IQ4_NL15.0 GB 16.2 GB
Too big Get file →
Q4_K_S15.1 GB 16.3 GB
Too big Get file →
Q4_K_M16.1 GB 17.2 GB
Too big Get file →
Q4_K_L16.4 GB 17.6 GB
Too big Get file →
Q5_K_S18.2 GB 19.3 GB
Too big Get file →
Q5_K_M18.7 GB 19.9 GB
Too big Get file →
Q5_K_L19.0 GB 20.2 GB
Too big Get file →
Q6_K21.6 GB 22.8 GB
Too big Get file →
Q6_K_L21.8 GB 23.0 GB
Too big Get file →
Q8_027.9 GB 29.1 GB
Too big Get file →
F1652.5 GB 53.7 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XS (8.2 GB) or Q2_K_L (10.36 GB) which require about 9–11.5 GB memory at 8‑k context. For 16‑GB VRAM, Q4_K_M (16.06 GB) or Q5_K_S (18.16 GB) are suitable, needing roughly 17–19 GB memory. For 32‑GB VRAM, Q6_K (21.57 GB) or Q8_0 (27.91 GB) provide higher fidelity with memory estimates of 22.8–29.1 GB.

What GPU do you need for Ornith 1.5 27B A3B CoderX 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: the best quant that fits is the main file (0.1 GB file, about 1.3 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.3 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q2_K_L (10.4 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ4_XS (14.2 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K_L (21.8 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (27.9 GB file, about 29.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (27.9 GB file, about 29.1 GB in use).

Which Ornith 1.5 27B A3B CoderX MTP quant should you choose?

Q4_K_M is the usual starting point for Ornith 1.5 27B A3B CoderX MTP: it balances file size and quality well. Here it is a 16.1 GB file.

The Q8_0 file is 27.9 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters26.2B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized byManniX-ITA
FamilyOrnith
Licenseapache-2.0
Downloads (HF)3,434
Last updated2026-09-16

Frequently asked questions about Ornith 1.5 27B A3B CoderX MTP

How much VRAM does Ornith 1.5 27B A3B CoderX MTP need?

About 17.2 GB at Q4_K_M with an 8K context window. That is the 16.1 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 1.5 27B A3B CoderX MTP on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ornith 1.5 27B A3B CoderX MTP GGUF?

It depends on the quant: file is 0.1 GB, IQ2_XS is 8.2 GB, IQ2_M is 9.1 GB, Q2_K_L is 10.4 GB, Q3_K_S is 11.5 GB, IQ3_M is 11.7 GB and 15 more.

What context length does Ornith 1.5 27B A3B CoderX 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 1.5 27B A3B CoderX MTP GGUF?

The files are on Hugging Face in the ManniX-ITA/Ornith-1.5-27B-A3B-CoderX-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 1.5 27B A3B CoderX MTP 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 Ornith 1.5 27B A3B CoderX on 8 GB VRAM?

Yes, using the IQ2_XS or Q2_K_L quantizations which fit within 8‑GB VRAM and require about 9–11.5 GB memory at 8‑k context.

Does the model support vision tasks?

Yes, the model has detected vision abilities and includes a speculative MTP head.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Ornith-1.5-27B-A3B-CoderX

Similar models

Browse all →

More from ManniX-ITA

All by ManniX-ITA →

More Ornith models

All Ornith →

Other medium models

All medium models →