QW

Qwen3.5 4B SOMPOA heresy v2 TPN

QwenGGUF by tpnlabsUpdated 2026-10-22
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.7 GB
Quick answer

Qwen3.5 4B SOMPOA heresy v2 TPN 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 2 quants, from 2.7 GB (Q4_K_M) to 4.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Qwen3.5 4B SOMPOA heresy v2 TPN – a fine‑tuned Qwen3.5 model

Qwen3.5 4B SOMPOA heresy v2 TPN is a 4.21 billion‑parameter model fine‑tuned with SOMPOA ablation. It supports reasoning, tools, and vision. The model is released under apache‑2.0 and is compatible with llama.cpp, vLLM, and other frameworks.

Good at

  • Reasoning
  • Tools integration
  • Vision tasks

Limits

  • No vision support on older runtimes
  • Requires 8 k context for memory estimates
  • License is apache‑2.0

Best for

  • Chatbot development
  • Code generation
  • Multimodal inference

Who it’s for. Developers needing a small yet capable Qwen3.5 variant for local deployment. The model is suitable for projects that require reasoning, tool use, and vision within a 4‑billion‑parameter footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.7 GB 4.3 GB
Fits Get file →
Q8_04.5 GB 6.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (2.71 GB file, ~4.3 GB RAM at 8 k context). If 12 GB VRAM is available, Q8_0 (4.48 GB file, ~6.1 GB RAM) offers higher fidelity. Memory estimates are approximate.

What GPU do you need for Qwen3.5 4B SOMPOA heresy v2 TPN?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (2.7 GB file, about 4.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).

Which Qwen3.5 4B SOMPOA heresy v2 TPN quant should you choose?

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

The Q8_0 file is 4.5 GB, about 1.7 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.

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 bytpnlabs
FamilyQwen
Licenseapache-2.0
Downloads (HF)625
Last updated2026-10-22

Frequently asked questions about Qwen3.5 4B SOMPOA heresy v2 TPN

How much VRAM does Qwen3.5 4B SOMPOA heresy v2 TPN 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 SOMPOA heresy v2 TPN on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 4B SOMPOA heresy v2 TPN GGUF?

It depends on the quant: Q4_K_M is 2.7 GB, Q8_0 is 4.5 GB.

What context length does Qwen3.5 4B SOMPOA heresy v2 TPN 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 SOMPOA heresy v2 TPN GGUF?

The files are on Hugging Face in the tpnlabs/Qwen3.5-4B-SOMPOA-heresy-v2-TPN-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 SOMPOA heresy v2 TPN 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 Q4_K_M quantized file is 2.71 GB and requires about 4.3 GB RAM at 8 k context, fitting comfortably in 8 GB VRAM.

Does this model support vision?

Yes, it has detected vision ability, but older runtimes may need metadata fixes to load correctly.

What license applies to this model?

The model is released under the apache‑2.0 license.

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

Similar models

Browse all →

More from tpnlabs

All by tpnlabs →

More Qwen models

All Qwen →

Other small models

All small models →