QW

fusewalk models

QwenGGUF by npatemanUpdated 2026-10-16
Download on Hugging Face
Parameters4.21B
Context40K
Layers28
Architectureqwen3
Smallest quant0.4 GB
Quick answer

fusewalk models needs about 2.5 GB of memory at its main file (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.4 GB to 2.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Fusewalk fine‑tuned 4‑bit Qwen3 model for item combination queries

Fusewalk models are fine‑tuned on the Fusewalk Codex to answer what two items combine into. They are 4‑bit (Q4_K_M) GGUFs for llama.cpp, derived from Qwen3‑0.6B. The models support up to 40960 context tokens and are released under Apache‑2.0.

Good at

  • Item combination prediction
  • Fast inference on low‑memory GPUs
  • Consistent prompt template usage

Limits

  • No vision or multimodal support
  • Requires 8‑k context for memory estimates
  • Only supports the specified prompt template

Best for

  • Crafting game assistants
  • Educational tools for item recipes
  • Rapid prototyping of fine‑tuned LLMs

Who it’s for. Developers building game AI or educational tools that need quick, accurate item combination answers. The models are lightweight and easy to deploy with llama.cpp or other GGUF‑compatible runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.4 GB 1.8 GB
Fits Get file →
—1.1 GB 2.5 GB
Fits Get file →
—1.1 GB 2.5 GB
Fits Get file →
—2.7 GB 4.1 GB
Fits Get file →

For 8‑GB VRAM, the 0.4‑GB model uses about 1.8‑GB memory at 8‑k context, suitable for low‑budget setups. The 1.11‑GB model uses about 2.5‑GB memory and offers a balance between size and performance. For higher VRAM (12‑GB+), the 2.71‑GB model uses about 4.1‑GB memory and provides the largest context handling.

What GPU do you need for fusewalk models?

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 (1.1 GB file, about 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (2.7 GB file, about 4.1 GB in use).

Which fusewalk models quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.4 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

Architectureqwen3
Parameters4.21B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized bynpateman
FamilyQwen
Base modelQwen/Qwen3-0.6B
Licenseapache-2.0
Downloads (HF)1,299
Last updated2026-10-16

Frequently asked questions about fusewalk models

How much VRAM does fusewalk models need?

About 2.5 GB at its main file with an 8K context window. That is the 1.1 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 fusewalk models on an 8 GB GPU?

Yes, with the smaller files: the 2.7 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of fusewalk models GGUF?

It depends on the quant: file is 0.4 GB, file is 1.1 GB, file is 1.1 GB, file is 2.7 GB.

What context length does fusewalk models support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download fusewalk models GGUF?

The files are on Hugging Face in the npateman/fusewalk-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does fusewalk models 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 the 0.4‑GB model on 8 GB VRAM?

Yes, it requires approximately 1.8‑GB memory at 8‑k context, leaving room for other processes.

Does the model support image input?

No, the Fusewalk models are purely text‑based and do not include vision capabilities.

What license applies to these models?

They are released under the Apache‑2.0 license, as inherited from the base Qwen3 model.

Other GGUFs of Qwen3-0.6B

Similar models

Browse all →

More Qwen models

All Qwen →

Other small models

All small models →