QW

Homunculus

QwenGGUF by QuantFactoryUpdated 2025-06-21
Download on Hugging Face
Parameters12.5B
Context128K
Layers40
Architecturellama
Smallest quant4.9 GB
Quick answer

Homunculus needs about 9.5 GB of memory at Q4_K_M (a 7.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.9 GB (Q2_K) to 13.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Homunculus – 12.5B parameter model distilled from Qwen3 for single‑GPU use

Homunculus is a 12.5B parameter instruction model distilled from Qwen3-235B-A22B onto the Mistral‑Nemo backbone. It preserves Qwen’s two‑mode interaction style, offering both deliberate chain‑of‑thought and concise answers. The model is available in multiple GGUF quantizations for efficient inference.

Good at

  • Reasoning and chain‑of‑thought tasks
  • Tool integration and agent capabilities
  • Instruction following in two modes

Limits

  • No vision support
  • Requires at least 8k context for estimates
  • License is apache‑2.0

Best for

  • Research on reasoning‑trace distillation
  • Lightweight product demos on consumer GPUs
  • Testing mode‑switchable assistants

Who it’s for. Developers and researchers who need a compact, mode‑switchable assistant for reasoning and tool use. It is suitable for single‑GPU inference and lightweight product prototypes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.9 GB 6.8 GB
Fits Get file →
Q3_K_S5.7 GB 7.5 GB
Tight Get file →
Q3_K_M6.2 GB 8.1 GB
Too big Get file →
Q3_K_L6.7 GB 8.5 GB
Too big Get file →
Q4_07.2 GB 9.1 GB
Too big Get file →
Q4_K_S7.3 GB 9.1 GB
Too big Get file →
Q4_K_M7.6 GB 9.5 GB
Too big Get file →
Q4_17.9 GB 9.8 GB
Too big Get file →
Q5_08.7 GB 10.5 GB
Too big Get file →
Q5_K_S8.7 GB 10.5 GB
Too big Get file →
Q5_K_M8.9 GB 10.7 GB
Too big Get file →
Q5_19.4 GB 11.2 GB
Too big Get file →
Q6_K10.2 GB 12.1 GB
Too big Get file →
Q8_013.2 GB 15.1 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (est. 9.5 GB) or Q4_0 (est. 9.1 GB). With 12 GB VRAM Q5_K_M (est. 10.7 GB) or Q6_K (est. 12.1 GB) are suitable. Larger GPUs can run Q8_0 (est. 15.1 GB).

What GPU do you need for Homunculus?

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: the best quant that fits is Q3_K_S (5.7 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_1 (9.4 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.2 GB file, about 15.1 GB in use).

Which Homunculus quant should you choose?

Q4_K_M is the usual starting point for Homunculus: it balances file size and quality well. Here it is a 7.6 GB file.

The Q8_0 file is 13.2 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 4.9 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

Architecturellama
Parameters12.5B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byQuantFactory
FamilyQwen
Licenseapache-2.0
Downloads (HF)600
Last updated2025-06-21

Frequently asked questions about Homunculus

How much VRAM does Homunculus need?

About 9.5 GB at Q4_K_M with an 8K context window. That is the 7.6 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 Homunculus on an 8 GB GPU?

Yes, with Q3_K_S: the 5.7 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Homunculus GGUF?

It depends on the quant: Q2_K is 4.9 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.2 GB, Q3_K_L is 6.7 GB, Q4_0 is 7.2 GB, Q4_K_S is 7.3 GB and 8 more.

What context length does Homunculus support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Homunculus GGUF?

The files are on Hugging Face in the QuantFactory/Homunculus-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 Homunculus 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 Homunculus on 8 GB VRAM?

Yes, using Q4_K_M or Q4_0 quantizations which estimate 9.5 GB and 9.1 GB of VRAM at 8k context.

Does Homunculus support vision?

No, the model has no vision capabilities.

What license applies to Homunculus?

The model is licensed under apache‑2.0.

Other GGUFs of Qwen3-235B-A22B

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Qwen models

All Qwen →

Other medium models

All medium models →