IN

Ingot VI 27B Q2

IngotGGUF by dendriteholdingsUpdated 2026-10-29
Download on Hugging Face
Parameters26.9B
Context256K
Layers64
Architectureqwen35
Smallest quant7.2 GB
Quick answer

Ingot VI 27B Q2 needs about 9.9 GB of memory at its main file (a 7.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Ingot VI 27B Q2 – a 26.9B Qwen‑35 model for reasoning and tool use

Ingot VI 27B Q2 is a 26.9 billion‑parameter Qwen‑35 model released by dendriteholdings. It supports reasoning and tool‑use tasks. The gguf file is 7.21 GB and requires approximately 9.9 GB of VRAM at 8 k context.

Good at

  • Reasoning
  • Tool use
  • Large context handling

Limits

  • No vision support by default
  • Requires PrismML fork of llama.cpp
  • License not specified

Best for

  • Chatbot back‑end
  • Code generation with tool calls
  • Long‑form reasoning tasks

Who it’s for. Developers and researchers needing a large‑context language model with reasoning and tool‑use capabilities. The model is suitable for applications that can run the PrismML fork of llama.cpp and have sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.2 GB 9.9 GB
Too big Get file →

The provided gguf file is quantized with an unknown scheme and is 7.21 GB in size. It needs about 9.9 GB of VRAM at 8 k context. For systems with 8 GB VRAM, a smaller quantization such as Q4_K_M would be required, but such a file is not available here. For 12 GB VRAM, the current file can be used directly.

What GPU do you need for Ingot VI 27B Q2?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (7.2 GB file, about 9.9 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters26.9B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized bydendriteholdings
FamilyIngot
Downloads (HF)6,267
Last updated2026-10-29

Frequently asked questions about Ingot VI 27B Q2

How much VRAM does Ingot VI 27B Q2 need?

About 9.9 GB at its main file with an 8K context window. That is the 7.2 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 Ingot VI 27B Q2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ingot VI 27B Q2 GGUF?

It depends on the quant: file is 7.2 GB.

What context length does Ingot VI 27B Q2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Ingot VI 27B Q2 GGUF?

The files are on Hugging Face in the dendriteholdings/Ingot-VI-27B-Q2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Ingot VI 27B Q2 on 8 GB VRAM?

The current gguf file requires approximately 9.9 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.

Does this model support image input?

The base model is text only. Image input requires adding a vision tower projector, but quality is untested.

Which llama.cpp fork is needed to run this model?

The PrismML fork of llama.cpp at commit e3de715 is required; stock llama.cpp does not support it.

Similar models

Browse all →

More from dendriteholdings

All by dendriteholdings →

More Ingot models

All Ingot →

Other medium models

All medium models →