Sanshoku Qwen3.8 3.6 27B blend needs about 10.3 GB of memory at its main file (a 7.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 6.3 GB to 8.0 GB (Q2_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Sanshoku Qwen3.8 3.6 27B blend – a ternary-quantized vision-capable LLM
Sanshoku Qwen3.8 3.6 27B blend is a ternary model distilled from Qwen3.6-27B and Qwen3.8-27B. It supports vision and has a native context length of 262,144 tokens. The model is released under Apache-2.0.
Good at
- Vision‑enabled language tasks
- Long‑context reasoning
- Coding agent scenarios
Limits
- No explicit vision limits beyond model size
- Requires at least 9 GB VRAM for the smallest quant
- License is Apache‑2.0
Best for
- Chatbots needing image input
- Code generation with large context
- Research on ternary quantization
Who it’s for. Developers and researchers who need a vision‑capable LLM with a large context window and who are comfortable working with GGUF files. The model is suitable for experimentation and production use under the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 6.3 GB | 9.0 GB | Too big | Get file → | |
| — | 7.6 GB | 10.3 GB | Too big | Get file → | |
| Q2_0 | 8.0 GB | 10.7 GB | Too big | Get file → |
For 8 GB VRAM, use the unknown‑quant 6.34 GB file (est. 9 GB memory). For 10 GB VRAM, the 7.61 GB file (est. 10.3 GB memory) is appropriate. If more VRAM is available, the Q2_0 8.03 GB file (est. 10.7 GB memory) offers the best trade‑off between size and precision.
What GPU do you need for Sanshoku Qwen3.8 3.6 27B blend?
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 Q2_0 (8.0 GB file, about 10.7 GB in use).
Which Sanshoku Qwen3.8 3.6 27B blend quant should you choose?
If memory is tight, the smallest file is the first one in the table at 6.3 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
Source
Frequently asked questions about Sanshoku Qwen3.8 3.6 27B blend
How much VRAM does Sanshoku Qwen3.8 3.6 27B blend need?
About 10.3 GB at its main file with an 8K context window. That is the 7.6 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 Sanshoku Qwen3.8 3.6 27B blend on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Sanshoku Qwen3.8 3.6 27B blend GGUF?
It depends on the quant: file is 6.3 GB, file is 7.6 GB, Q2_0 is 8.0 GB.
What context length does Sanshoku Qwen3.8 3.6 27B blend support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Sanshoku Qwen3.8 3.6 27B blend GGUF?
The files are on Hugging Face in the oshiteku/Sanshoku-Qwen3.8-3.6-27B-blend-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 Sanshoku Qwen3.8 3.6 27B blend 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 6.34 GB unknown‑quant file requires about 9 GB VRAM, so 8 GB VRAM is insufficient. Use a larger GPU or a smaller quant.
Does this model support vision?
Yes, the model has detected vision abilities and includes a vision encoder.
What license applies to this model?
The model is released under Apache‑2.0.