QW

Qwen3.6 14B A3B VibeForged v2

QwenGGUF by tvall43Updated 2026-05-29
Download on Hugging Face
Parameters13.8B
Context256K
Layers40
Architectureqwen35moe
Smallest quant5.3 GB
Quick answer

Qwen3.6 14B A3B VibeForged v2 needs about 9.6 GB of memory at Q4_K_M (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 5.3 GB (Q2_K) to 14.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Qwen3.6 14B A3B VibeForged v2 – a multimodal 14B MoE model optimized for local inference

Qwen3.6 14B A3B VibeForged v2 is a 14B parameter model with 3B active MoE parameters. It supports vision and strict XML reasoning blocks. The model is available in several GGUF quantizations for different VRAM budgets.

Good at

  • Vision and multimodal reasoning
  • XML‑structured reasoning
  • JSON tool‑calling

Limits

  • Requires 8‑bit or higher quant for best quality
  • No native support for 4‑bit quant on some engines
  • License is Apache‑2.0

Best for

  • Local inference on 8‑GB VRAM
  • Multimodal coding assistants
  • Tool‑calling workflows

Who it’s for. Developers and researchers who need a compact, multimodal LLM with MoE capabilities for local deployment. The model is suitable for applications that require vision input and structured reasoning output.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.3 GB 6.5 GB
Fits Get file →
Q3_K_M6.8 GB 7.9 GB
Tight Get file →
Q4_K_M8.5 GB 9.6 GB
Too big Get file →
MXFP4_MOE8.6 GB 9.8 GB
Too big Get file →
Q6_K11.3 GB 12.5 GB
Too big Get file →
Q8_014.7 GB 15.8 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (8.47 GB file, ~9.6 GB VRAM). If more VRAM is available, Q6_K or Q8_0 provide higher quality. For very limited memory, Q2_K or Q3_K_M are options but with reduced performance.

What GPU do you need for Qwen3.6 14B A3B VibeForged v2?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q3_K_M (6.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is MXFP4_MOE (8.6 GB file, about 9.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (14.7 GB file, about 15.8 GB in use).

Which Qwen3.6 14B A3B VibeForged v2 quant should you choose?

Q4_K_M is the usual starting point for Qwen3.6 14B A3B VibeForged v2: it balances file size and quality well. Here it is a 8.5 GB file.

The Q8_0 file is 14.7 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.

If memory is tight, the smallest file is Q2_K at 5.3 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

Architectureqwen35moe
Parameters13.8B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bytvall43
FamilyQwen
Licenseapache-2.0
Downloads (HF)6,665
Last updated2026-05-29

Frequently asked questions about Qwen3.6 14B A3B VibeForged v2

How much VRAM does Qwen3.6 14B A3B VibeForged v2 need?

About 9.6 GB at Q4_K_M with an 8K context window. That is the 8.5 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 Qwen3.6 14B A3B VibeForged v2 on an 8 GB GPU?

Yes, with Q3_K_M: the 6.8 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.6 14B A3B VibeForged v2 GGUF?

It depends on the quant: Q2_K is 5.3 GB, Q3_K_M is 6.8 GB, Q4_K_M is 8.5 GB, MXFP4_MOE is 8.6 GB, Q6_K is 11.3 GB, Q8_0 is 14.7 GB.

What context length does Qwen3.6 14B A3B VibeForged v2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Qwen3.6 14B A3B VibeForged v2 GGUF?

The files are on Hugging Face in the tvall43/Qwen3.6-14B-A3B-VibeForged-v2-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 Qwen3.6 14B A3B VibeForged v2 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 Qwen3.6 14B A3B VibeForged v2 on 8 GB VRAM?

Yes, the Q4_K_M quantization fits in 8 GB VRAM with an estimated 9.6 GB usage at 8k context.

Does this model support vision?

Yes, it includes multimodal projector files for vision tasks.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Qwen3.6-14B-A3B-VibeForged-v2

Similar models

Browse all →

More from tvall43

All by tvall43 →

More Qwen models

All Qwen →

Other medium models

All medium models →