QW

Qwen3.5 0.8B Heretic

QwenGGUF by saidutta69Updated 2026-10-28
Download on Hugging Face
Parameters752M
Context256K
Layers25
Architectureqwen35
Smallest quant0.4 GB
Quick answer

Qwen3.5 0.8B Heretic needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.4 GB (Q2_K) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.

Qwen3.5 0.8B Heretic – a small, fast, uncensored Qwen3.5 variant

Qwen3.5 0.8B Heretic is a 0.8B parameter causal language model with a hybrid linear‑attention core. It is a decensored variant of Qwen3.5‑0.8B, produced with Heretic ablation to suppress refusal behavior while preserving base capabilities. The model supports long context and runs on CPU and edge devices.

Good at

  • Fast inference on low‑VRAM GPUs
  • Long‑context handling up to 262144 tokens
  • Uncensored instruction following

Limits

  • No vision support
  • No safety filtering
  • Requires 8k context for memory estimates

Best for

  • Edge device inference
  • Rapid prototyping
  • Fine‑tuning research

Who it’s for. Developers who need a lightweight Qwen3.5 model without refusal guardrails. The 0.8B hybrid linear‑attention core runs on CPU and edge devices, offering strong speed and long‑context handling for its size.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.4 GB 1.3 GB
Fits Get file →
Q3_K_S0.4 GB 1.4 GB
Fits Get file →
IQ3_S0.5 GB 1.4 GB
Fits Get file →
Q3_K_M0.5 GB 1.4 GB
Fits Get file →
Q3_K_L0.5 GB 1.4 GB
Fits Get file →
Q4_00.5 GB 1.4 GB
Fits Get file →
Q4_K_S0.5 GB 1.4 GB
Fits Get file →
IQ4_XS0.5 GB 1.4 GB
Fits Get file →
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q4_10.5 GB 1.5 GB
Fits Get file →
Q5_K_S0.6 GB 1.5 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.6 GB 1.5 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K (0.5 GB file, ~1.4 GB memory at 8k context). If you have 4 GB VRAM, drop to Q2_K (0.42 GB file, ~1.3 GB memory). For 16 GB VRAM, any quant up to Q8_0 works comfortably. Memory estimates are approximate.

What GPU do you need for Qwen3.5 0.8B Heretic?

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 F16 (1.5 GB file, about 2.4 GB in use).

Which Qwen3.5 0.8B Heretic quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 0.8B Heretic: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.5 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 0.4 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

Architectureqwen35
Parameters752M
Layers25
Trained context262,144 tokens
KV cache (fp16)50 KB per token

Source

Quantized bysaidutta69
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,073
Last updated2026-10-28

Frequently asked questions about Qwen3.5 0.8B Heretic

How much VRAM does Qwen3.5 0.8B Heretic need?

About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 0.8B Heretic on an 8 GB GPU?

Yes, with F16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 0.8B Heretic GGUF?

It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, IQ3_S is 0.5 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_0 is 0.5 GB and 9 more.

What context length does Qwen3.5 0.8B Heretic support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.

Where can I download Qwen3.5 0.8B Heretic GGUF?

The files are on Hugging Face in the saidutta69/Qwen3.5-0.8B-heretic 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 0.8B Heretic 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 Qwen3.5 0.8B Heretic on 8 GB VRAM?

Yes, the Q4_K quant uses about 1.4 GB of VRAM at 8k context, leaving headroom for other processes.

Does this model support vision input?

No, it is a text‑only causal language model.

Is there a safety filter on this model?

No, refusal suppression is built into the weights; no additional safety filtering is applied.

Other GGUFs of Qwen3.5-0.8B

Similar models

Browse all →

More from saidutta69

All by saidutta69 →

More Qwen models

All Qwen →

Other tiny models

All tiny models →