QW

Qwen3.5 2B heretic imatrix

QwenGGUF by FadedRedStarUpdated 2026-07-10
Download on Hugging Face
Parameters331M
Context256K
Layers24
Architectureqwen35
Smallest quant0.6 GB
Quick answer

Qwen3.5 2B heretic imatrix needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.6 GB (Q8_0) to 1.4 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Qwen3.5 2B heretic imatrix – 2B parameter model with vision and coding abilities

Qwen3.5 2B heretic imatrix is a 0.331 billion parameter model from the Qwen family. It supports coding and vision tasks and is available in several GGUF quantizations. The model is released under the apache-2.0 license.

Good at

  • Coding tasks
  • Vision inference
  • Multimodal reasoning

Limits

  • No explicit vision support in all quantizations
  • Large context requires 262144 tokens
  • License is apache-2.0

Best for

  • Prototype multimodal applications
  • Fine‑tune for coding assistants
  • Research on vision‑language models

Who it’s for. Developers and researchers needing a compact multimodal model for prototyping or fine‑tuning. The model is suitable for environments with limited GPU memory but sufficient VRAM for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.6 GB 1.5 GB
Fits Get file →
BF161.0 GB 1.9 GB
Fits Get file →
IQ4_NL1.2 GB 2.1 GB
Fits Get file →
Q4_K_M1.3 GB 2.2 GB
Fits Get file →
Q5_K_M1.4 GB 2.3 GB
Fits Get file →

For 8 GB VRAM, Q8_0 (0.55 GB) or BF16 (1.03 GB) are suitable, using about 1.5 GB or 1.9 GB of VRAM at 8 k context. If VRAM is 4 GB, Q4_K_M (1.27 GB) or IQ4_NL (1.23 GB) can be used, estimating 2.2 GB or 2.1 GB of VRAM. For 2 GB VRAM, Q5_K_M (1.41 GB) is the largest option, using about 2.3 GB of VRAM.

What GPU do you need for Qwen3.5 2B heretic imatrix?

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 Q5_K_M (1.4 GB file, about 2.3 GB in use).

Which Qwen3.5 2B heretic imatrix quant should you choose?

Q4_K_M is the usual starting point for Qwen3.5 2B heretic imatrix: it balances file size and quality well. Here it is a 1.3 GB file.

The Q8_0 file is 0.6 GB, about 0.4 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 Q8_0 at 0.6 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters331M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byFadedRedStar
FamilyQwen
Licenseapache-2.0
Downloads (HF)730
Last updated2026-07-10

Frequently asked questions about Qwen3.5 2B heretic imatrix

How much VRAM does Qwen3.5 2B heretic imatrix need?

About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Qwen3.5 2B heretic imatrix on an 8 GB GPU?

Yes, with Q5_K_M: the 1.4 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 2B heretic imatrix GGUF?

It depends on the quant: Q8_0 is 0.6 GB, BF16 is 1.0 GB, IQ4_NL is 1.2 GB, Q4_K_M is 1.3 GB, Q5_K_M is 1.4 GB.

What context length does Qwen3.5 2B heretic imatrix 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 1.6 GB at 32K.

Where can I download Qwen3.5 2B heretic imatrix GGUF?

The files are on Hugging Face in the FadedRedStar/Qwen3.5-2B-heretic-imatrix-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 2B heretic imatrix 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 2B heretic imatrix on 8 GB VRAM?

Yes. Use Q8_0 or BF16 quantizations; they require about 1.5 GB or 1.9 GB of VRAM at 8 k context.

What is the memory requirement for the Q4_K_M quantization?

The Q4_K_M file is 1.27 GB and estimates 2.2 GB of VRAM at 8 k context.

Does the model support vision tasks in all quantizations?

The model has vision capability, but some quantizations may not include the vision projection matrix; check the repository for details.

Other GGUFs of Qwen3.5-2B-heretic

Similar models

Browse all →

More from FadedRedStar

All by FadedRedStar →

More Qwen models

All Qwen →

Other tiny models

All tiny models →