QW

Heretic Qwen3 VL 235B A22B Instruct i1

QwenGGUF by mradermacherUpdated 2026-09-11
Download on Hugging Face
Parameters235B
Context—
Layers—
Architecture—
Smallest quant0.5 GB
Quick answer

Heretic Qwen3 VL 235B A22B Instruct i1 needs about 108.0 GB of memory at IQ3_XS (a 96.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 17 quants, from 0.5 GB to 166.8 GB (Q5_K_M).

Heretic Qwen3 VL 235B A22B Instruct i1 – a vision‑enabled large language model

Heretic Qwen3 VL 235B A22B Instruct i1 is a 235 billion‑parameter model adapted for vision tasks. It is released under the apache‑2.0 license and available in multiple GGUF quantizations. The model supports instruction following and multimodal input.

Good at

  • Vision‑enabled instruction following
  • Multimodal content generation
  • Large‑context reasoning

Limits

  • No vision support in some quant types
  • Limited refusal handling
  • Requires fine‑tuning for sensitive queries

Best for

  • Chatbots with image inputs
  • Content creation with visual context
  • Rapid prototyping of multimodal LLMs

Who it’s for. Developers and researchers needing a large vision‑enabled LLM for experimentation. The model is suitable for those who can manage the memory demands of the higher‑quality quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 1.0 GB
Fits Get file →
IQ1_S47.9 GB 54.2 GB
Too big Get file →
IQ1_M53.1 GB 60.0 GB
Too big Get file →
IQ2_XXS61.8 GB 69.7 GB
Too big Get file →
IQ2_XS68.8 GB 77.6 GB
Too big Get file →
IQ2_S70.2 GB 79.2 GB
Too big Get file →
IQ2_M77.2 GB 86.9 GB
Too big Get file →
Q2_K_S79.8 GB 89.8 GB
Too big Get file →
IQ3_XS96.0 GB 108.0 GB
Too big Get file →
Q3_K_S101.4 GB 114.1 GB
Too big Get file →
IQ3_S101.5 GB 114.1 GB
Too big Get file →
Q3_K_L121.8 GB 136.9 GB
Too big Get file →
IQ4_XS125.3 GB 140.8 GB
Too big Get file →
Q4_0133.1 GB 149.6 GB
Too big Get file →
Q4_1147.2 GB 165.4 GB
Too big Get file →
Q5_K_S161.9 GB 181.8 GB
Too big Get file →
Q5_K_M166.8 GB 187.3 GB
Too big Get file →

For 8 GB VRAM use the IQ1_S quant (file size 47.95 GB, memory 54.2 GB). For 16 GB VRAM the IQ2_XS quant (file size 68.82 GB, memory 77.6 GB) is recommended. For 24 GB VRAM the Q4_0 quant (file size 133.13 GB, memory 149.6 GB) offers a balance between size and performance. Memory estimates are approximate.

What GPU do you need for Heretic Qwen3 VL 235B A22B Instruct i1?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.5 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).

Which Heretic Qwen3 VL 235B A22B Instruct i1 quant should you choose?

IQ3_XS (96.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is the first one in the table at 0.5 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

Parameters235B

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)982
Last updated2026-09-11

Frequently asked questions about Heretic Qwen3 VL 235B A22B Instruct i1

How much VRAM does Heretic Qwen3 VL 235B A22B Instruct i1 need?

About 108.0 GB at IQ3_XS with an 8K context window. That is the 96.0 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 Heretic Qwen3 VL 235B A22B Instruct i1 on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Heretic Qwen3 VL 235B A22B Instruct i1 GGUF?

It depends on the quant: file is 0.5 GB, IQ1_S is 47.9 GB, IQ1_M is 53.1 GB, IQ2_XXS is 61.8 GB, IQ2_XS is 68.8 GB, IQ2_S is 70.2 GB and 11 more.

Where can I download Heretic Qwen3 VL 235B A22B Instruct i1 GGUF?

The files are on Hugging Face in the mradermacher/Heretic-Qwen3-VL-235B-A22B-Instruct-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 Heretic Qwen3 VL 235B A22B Instruct i1 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?

The smallest quant suitable for 8 GB VRAM is IQ1_S, which requires about 54.2 GB of memory at 8k context. This exceeds 8 GB, so it is not feasible.

Does the model support vision tasks?

Yes, the model is a vision‑enabled LLM. Vision files (mmproj) are available in the static repository.

What license does the model use?

The model is released under the apache‑2.0 license.

Other GGUFs of Heretic-Qwen3-VL-235B-A22B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →