QW

Qwen2.5 VL 32B Instruct Heretic

QwenGGUF by mradermacherUpdated 2026-01-18
Download on Hugging Face
Parameters32.8B
Context125K
Layers64
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

Qwen2.5 VL 32B Instruct Heretic needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 26.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Qwen2.5 VL 32B Instruct Heretic – a 32‑billion‑parameter vision‑language model

Qwen2.5 VL 32B Instruct Heretic is a 32‑billion‑parameter model that supports vision and coding tasks. It is trained on 128,000 context tokens and released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Vision‑language reasoning
  • Structured output generation
  • Agentic tool use

Limits

  • Large VRAM requirement for full precision
  • No native vision support in some runtimes
  • Requires 128k context for full capability

Best for

  • Image captioning with structured JSON
  • Video event extraction
  • Visual coding assistance

Who it’s for. Developers needing a high‑capacity vision‑language model for complex reasoning and structured output. The model is suitable for research and production environments that can accommodate its memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ1_S7.3 GB 9.9 GB
Too big Get file →
IQ1_M7.9 GB 10.6 GB
Too big Get file →
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_XS10.0 GB 12.6 GB
Too big Get file →
IQ2_S10.4 GB 13.0 GB
Too big Get file →
IQ2_M11.3 GB 13.9 GB
Too big Get file →
Q2_K_S11.5 GB 14.1 GB
Too big Get file →
Q2_K12.3 GB 15.0 GB
Too big Get file →
IQ3_XXS12.8 GB 15.5 GB
Too big Get file →
IQ3_XS13.7 GB 16.4 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.4 GB 17.1 GB
Too big Get file →
IQ3_M14.8 GB 17.5 GB
Too big Get file →
Q3_K_M15.9 GB 18.6 GB
Too big Get file →
Q3_K_L17.2 GB 19.9 GB
Too big Get file →
IQ4_XS17.7 GB 20.3 GB
Too big Get file →
Q4_018.7 GB 21.4 GB
Too big Get file →
Q4_K_S18.8 GB 21.4 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q4_120.6 GB 23.3 GB
Too big Get file →
Q5_K_S22.6 GB 25.3 GB
Too big Get file →
Q5_K_M23.3 GB 25.9 GB
Too big Get file →
Q6_K26.9 GB 29.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (7.27 GB) or IQ1_M (7.93 GB). For 16 GB VRAM, IQ2_S (9.96 GB) or Q2_K (12.31 GB) are suitable. For 24 GB VRAM, Q3_K_M (15.94 GB) or Q4_K_M (19.85 GB) provide a balance of size and performance. Memory estimates are approximate.

What GPU do you need for Qwen2.5 VL 32B Instruct 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 the main file (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_1 (20.6 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.9 GB file, about 29.5 GB in use).

Which Qwen2.5 VL 32B Instruct Heretic quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 VL 32B Instruct Heretic: it balances file size and quality well. Here it is a 19.9 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

Architectureqwen2vl
Parameters32.8B
Layers64
Trained context128,000 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)4,746
Last updated2026-01-18

Frequently asked questions about Qwen2.5 VL 32B Instruct Heretic

How much VRAM does Qwen2.5 VL 32B Instruct Heretic need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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 Qwen2.5 VL 32B Instruct Heretic on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2.5 VL 32B Instruct Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.3 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.4 GB and 18 more.

What context length does Qwen2.5 VL 32B Instruct Heretic support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Qwen2.5 VL 32B Instruct Heretic GGUF?

The files are on Hugging Face in the mradermacher/Qwen2.5-VL-32B-Instruct-heretic-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 Qwen2.5 VL 32B Instruct 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 Qwen2.5 VL 32B Instruct Heretic on 8 GB VRAM?

Use the IQ1_S or IQ1_M quantizations; they require about 9–10 GB VRAM at 8k context.

Does the model support vision tasks?

Yes, it can recognize objects, analyze text in images, and generate structured outputs.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen2.5-VL-32B-Instruct-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other medium models

All medium models →