Qwen3.8 3.6 27B blend needs about 1.8 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 1.1 GB (Q4_K_M) to 19.5 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
JetBrains Qwen3.8‑3.6‑27B‑blend, 27 B parameters, vision‑capable GGUF model
The Qwen3.8‑3.6‑27B‑blend is a 27 B parameter model created by linearly interpolating Qwen3.6‑27B and Qwen3.8‑27B checkpoints. It supports vision tasks and is distributed under Apache‑2.0. The model is available in multiple GGUF quantizations.
Good at
- Vision‑enabled text generation
- Large context handling up to 262 144 tokens
- Flexible quantization for memory trade‑offs
Limits
- Requires recent llama.cpp with Qwen3.5 MTP support
- No dedicated vision projector file included
- License requires attribution per Apache‑2.0
Best for
- Developers needing vision‑enabled LLMs on local hardware
- Researchers testing blended Qwen architectures
- Applications requiring large context windows
Who it’s for. This model is suited for developers and researchers who need a vision‑capable, large‑context LLM on local hardware. It is ideal for those who can run recent llama.cpp builds and want to experiment with blended Qwen checkpoints.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.1 GB | 1.8 GB | Fits | Get file → | |
| BF16 | 3.9 GB | 4.5 GB | Fits | Get file → | |
| IQ3_S | 12.6 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_XL | 13.1 GB | 13.8 GB | Too big | Get file → | |
| IQ4_XS | 14.3 GB | 14.9 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 17.5 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 20.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_S (12.6 GB file, ~15.3 GB RAM at 8 k context). For 12 GB VRAM, Q3_K_XL (13.15 GB, ~15.8 GB RAM). For 16 GB VRAM, IQ4_XS (14.25 GB, ~16.9 GB RAM). Larger quants need more memory.
What GPU do you need for 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: the best quant that fits is Q4_K_M (1.1 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.9 GB file, about 4.5 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (3.9 GB file, about 4.5 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (3.9 GB file, about 4.5 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (14.3 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.5 GB file, about 20.2 GB in use).
Which Qwen3.8 3.6 27B blend quant should you choose?
Q4_K_M is the usual starting point for Qwen3.8 3.6 27B blend: it balances file size and quality well. Here it is a 1.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.8 3.6 27B blend
How much VRAM does Qwen3.8 3.6 27B blend need?
About 1.8 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Qwen3.8 3.6 27B blend on an 8 GB GPU?
Yes, with BF16: the 3.9 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.8 3.6 27B blend GGUF?
It depends on the quant: Q4_K_M is 1.1 GB, BF16 is 3.9 GB, IQ3_S is 12.6 GB, Q3_K_XL is 13.1 GB, IQ4_XS is 14.3 GB, Q4_K_M is 16.8 GB and 1 more.
What context length does 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 0.2 GB at 8K and 0.7 GB at 32K.
Where can I download Qwen3.8 3.6 27B blend GGUF?
The files are on Hugging Face in the JetBrains/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 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?
Yes, using the IQ3_S quant which requires about 15.3 GB RAM at 8 k context, fitting within 8 GB VRAM with swap.
Does this model support image input?
Yes, it is vision‑capable; use the provided mmproj file with the --mmproj flag in llama.cpp.
What license applies to this model?
Apache License, Version 2.0, with attribution required for JetBrains contributions.