PH

phase 3

PhaseGGUF by owenisasUpdated 2026-06-04
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant33.6 GB
Quick answer

phase 3 needs about 41.1 GB of memory at Q8_0 (a 33.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

phase 3 is a 31.6B-parameter Phase model in GGUF format, quantized by owenisas. Its trained context length is 1024K tokens. The repository has 1 quant file, from 33.6 GB (Q8_0) to 33.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_033.6 GB 41.1 GB
Too big Get file →

What GPU do you need for phase 3?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q8_0 (33.6 GB file, about 41.1 GB in use).

Which phase 3 quant should you choose?

Q8_0 (33.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters31.6B (approximate, mixture of experts)
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized byowenisas
FamilyPhase
Licensemit
Downloads (HF)22
Last updated2026-06-04

Frequently asked questions about phase 3

How much VRAM does phase 3 need?

About 41.1 GB at Q8_0 with an 8K context window. That is the 33.6 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 phase 3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 41.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of phase 3 GGUF?

It depends on the quant: Q8_0 is 33.6 GB.

What context length does phase 3 support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 27.9 GB at 32K.

Where can I download phase 3 GGUF?

The files are on Hugging Face in the owenisas/phase-3-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 phase 3 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.

Similar models

Browse all →

More from owenisas

All by owenisas →

More Phase models

All Phase →

Other medium models

All medium models →