QW

Qwen3.5 4B PaperWitch Heresy v2

QwenGGUF by mradermacherUpdated 2026-03-04
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant0.0 GB
Quick answer

Qwen3.5 4B PaperWitch Heresy v2 needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 3.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Qwen3.5 4B PaperWitch Heresy v2 – a fine‑tuned Qwen model

Qwen3.5 4B PaperWitch Heresy v2 is a 4.21 B parameter model fine‑tuned with the Heretic ablation engine. It supports reasoning and tool usage and is released under the Apache‑2.0 license.

Good at

  • Reasoning
  • Tool usage
  • Fine‑tuned behavior

Limits

  • No vision support
  • Large context requires high VRAM
  • No mixture of experts

Best for

  • Chat assistants
  • Code generation
  • Tool‑integrated workflows

Who it’s for. Developers needing a lightweight, reasoning‑capable LLM for integration into applications. The model is suitable for environments with limited GPU memory but sufficient RAM for 8 k context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S1.2 GB 2.7 GB
Fits Get file →
IQ1_M1.3 GB 2.8 GB
Fits Get file →
IQ2_XXS1.4 GB 3.0 GB
Fits Get file →
IQ2_XS1.5 GB 3.1 GB
Fits Get file →
IQ2_S1.5 GB 3.1 GB
Fits Get file →
IQ2_M1.6 GB 3.2 GB
Fits Get file →
Q2_K_S1.7 GB 3.3 GB
Fits Get file →
Q2_K1.8 GB 3.4 GB
Fits Get file →
IQ3_XXS1.8 GB 3.4 GB
Fits Get file →
IQ3_XS2.0 GB 3.6 GB
Fits Get file →
Q3_K_S2.1 GB 3.6 GB
Fits Get file →
IQ3_S2.1 GB 3.6 GB
Fits Get file →
IQ3_M2.2 GB 3.7 GB
Fits Get file →
Q3_K_M2.3 GB 3.8 GB
Fits Get file →
Q3_K_L2.4 GB 3.9 GB
Fits Get file →
IQ4_XS2.4 GB 4.0 GB
Fits Get file →
IQ4_NL2.5 GB 4.1 GB
Fits Get file →
Q4_02.5 GB 4.1 GB
Fits Get file →
Q4_K_S2.6 GB 4.1 GB
Fits Get file →
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q4_12.8 GB 4.3 GB
Fits Get file →
Q5_K_S3.0 GB 4.6 GB
Fits Get file →
Q5_K_M3.1 GB 4.7 GB
Fits Get file →
Q6_K3.5 GB 5.0 GB
Fits Get file →

For 8 k context, the IQ1_S quant uses 2.7 GB VRAM and 1.17 GB file size. If more memory is available, Q4_K_M uses 4.3 GB VRAM and 2.71 GB file size. The smallest quant, unknown, uses 1.6 GB VRAM but has a 0 GB file size placeholder.

What GPU do you need for Qwen3.5 4B PaperWitch Heresy v2?

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 IQ4_XS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.5 GB file, about 5.0 GB in use).

Which Qwen3.5 4B PaperWitch Heresy v2 quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 4B PaperWitch Heresy v2: it balances file size and quality well. Here it is a 2.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)454
Last updated2026-03-04

Frequently asked questions about Qwen3.5 4B PaperWitch Heresy v2

How much VRAM does Qwen3.5 4B PaperWitch Heresy v2 need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 Qwen3.5 4B PaperWitch Heresy v2 on an 8 GB GPU?

Yes, with Q6_K: the 3.5 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 4B PaperWitch Heresy v2 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.2 GB, IQ1_M is 1.3 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.5 GB and 19 more.

What context length does Qwen3.5 4B PaperWitch Heresy v2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Qwen3.5 4B PaperWitch Heresy v2 GGUF?

The files are on Hugging Face in the mradermacher/Qwen3.5-4B-PaperWitch-heresy-v2-i1-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 Qwen3.5 4B PaperWitch Heresy v2 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant requires 2.7 GB VRAM at 8 k context, well within an 8 GB budget.

Does this model support vision?

No, the model is not a vision model and does not include mmproj files.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.5-4B-PaperWitch-heresy-v2

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other small models

All small models →