QW

Qwythos-27B

QwythosGGUF by FastirazUpdated 2026-08-02
Download on Hugging Face
Parameters26.9B
Context1024K
Layers64
Architectureqwen35
Smallest quant17.3 GB
Quick answer

Qwythos-27B needs about 20.0 GB of memory at Q4_K_M (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 17.3 GB (Q4_K_M) to 54.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Qwythos‑27B: 27‑billion‑parameter Qwen3.5 model with full vision and 1M context

Qwythos‑27B is a 26.9‑billion‑parameter dense Qwen3.5 model. It retains native MTP, a full vision tower, and a 1,048,576‑token context window. The model is open‑weight, licensed under apache‑2.0.

Good at

  • Reasoning
  • Tool use
  • Vision

Limits

  • Large context requires high VRAM
  • No RL‑trained version yet
  • No ablation of features

Best for

  • Complex reasoning tasks
  • Tool‑enabled workflows
  • Vision‑based queries

Who it’s for. Researchers and developers needing a large, multi‑modal LLM with full context and tool‑calling capabilities. Suitable for technical, biomedical, and cybersecurity applications where uncensored responses are acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M17.3 GB 20.0 GB
Too big Get file →
Q4_K_M17.6 GB 20.3 GB
Too big Get file →
Q5_K_M19.8 GB 22.5 GB
Too big Get file →
Q5_K_M20.1 GB 22.8 GB
Too big Get file →
Q6_K22.5 GB 25.1 GB
Too big Get file →
Q6_K22.8 GB 25.5 GB
Too big Get file →
Q8_028.6 GB 31.2 GB
Too big Get file →
Q8_029.0 GB 31.7 GB
Too big Get file →
BF1653.8 GB 56.5 GB
Too big Get file →
BF1654.7 GB 57.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 17.31 GB, ~20 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (19.81 GB, ~22.5 GB memory). For 24 GB VRAM, Q6_K (22.45 GB, ~25.1 GB memory).

What GPU do you need for Qwythos-27B?

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 Q5_K_M (20.1 GB file, about 22.8 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 Qwythos-27B quant should you choose?

Q4_K_M is the usual starting point for Qwythos-27B: it balances file size and quality well. Here it is a 17.3 GB file.

The Q8_0 file is 28.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters26.9B
Layers64
Trained context1,048,576 tokens
KV cache (fp16)256 KB per token

Source

Quantized byFastiraz
FamilyQwythos
Licenseapache-2.0
Downloads (HF)586
Last updated2026-08-02

Frequently asked questions about Qwythos-27B

How much VRAM does Qwythos-27B need?

About 20.0 GB at Q4_K_M with an 8K context window. That is the 17.3 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 Qwythos-27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwythos-27B GGUF?

It depends on the quant: Q4_K_M is 17.3 GB, Q4_K_M is 17.6 GB, Q5_K_M is 19.8 GB, Q5_K_M is 20.1 GB, Q6_K is 22.5 GB, Q6_K is 22.8 GB and 4 more.

What context length does Qwythos-27B 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 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Qwythos-27B GGUF?

The files are on Hugging Face in the Fastiraz/Qwythos-27B-v1-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 Qwythos-27B 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 Qwythos‑27B on 8 GB VRAM?

Use the Q4_K_M quantized file; it requires about 20 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does the model support vision?

Yes, the full vision tower is preserved in all quantizations.

Is the model licensed for commercial use?

It is licensed under apache‑2.0, which allows commercial use with attribution.

Other GGUFs of Qwythos-27B-v1

Similar models

Browse all →

More from Fastiraz

All by Fastiraz →

More Qwythos models

All Qwythos →

Other medium models

All medium models →