Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2
Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2 needs about 20.0 GB of memory at its main file (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 3.2 GB (Q8_0) to 29.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Qwen3.8‑27B Coder390 EfficientThink – a 27 B multimodal LLM with coding and reasoning focus
This model is a 27 B Qwen architecture trained with SFT, RLOO, and DFlash2. It supports text, image, and video inputs and is licensed under Apache‑2.0. The model was trained on a 262 144‑token context window.
Good at
- Coding and code generation
- Multimodal reasoning with text, image, and video
- Long‑form text generation
Limits
- No vision support in some quantizations
- Large VRAM requirement for full‑precision
- License requires attribution
Best for
- Developers building code assistants
- Researchers needing multimodal LLMs
- Teams creating custom fine‑tuned models
Who it’s for. The model is suited for users who need a large, multimodal language model that can handle coding tasks and long‑context reasoning. It is ideal for developers, researchers, and enterprises that can provide the necessary GPU memory and comply with the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 3.2 GB | 5.8 GB | Fits | Get file → | |
| — | 13.3 GB | 16.0 GB | Too big | Get file → | |
| — | 13.3 GB | 16.0 GB | Too big | Get file → | |
| — | 13.5 GB | 16.2 GB | Too big | Get file → | |
| — | 17.3 GB | 20.0 GB | Too big | Get file → | |
| — | 17.5 GB | 20.2 GB | Too big | Get file → | |
| — | 19.6 GB | 22.3 GB | Too big | Get file → | |
| — | 19.8 GB | 22.5 GB | Too big | Get file → | |
| Q6_K | 23.2 GB | 25.9 GB | Too big | Get file → | |
| Q8_0 | 29.1 GB | 31.8 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8_0 quant (3.16 GB file, ~5.8 GB RAM). For 12 GB VRAM, Q6_K (23.18 GB file, ~25.9 GB RAM) is too large; instead use the 13.28 GB file (unknown quant) which needs ~16 GB RAM. For 16 GB VRAM, the 17.3 GB file (unknown quant) requires ~20 GB RAM. Choose the smallest file that fits your VRAM budget.
What GPU do you need for Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2?
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 Q8_0 (3.2 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 5.8 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (13.3 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (19.8 GB file, about 22.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (29.1 GB file, about 31.8 GB in use).
Which Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2 quant should you choose?
If memory is tight, the smallest file is Q8_0 at 3.2 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2
How much VRAM does Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2 need?
About 20.0 GB at its main file with an 8K context window. That is the 17.3 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 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2 on an 8 GB GPU?
Yes, with Q8_0: the 3.2 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2 GGUF?
It depends on the quant: Q8_0 is 3.2 GB, file is 13.3 GB, file is 13.3 GB, file is 13.5 GB, file is 17.3 GB, file is 17.5 GB and 4 more.
What context length does Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2 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 Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2 GGUF?
The files are on Hugging Face in the nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2 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 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2 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 Q8_0 quant file (3.16 GB) which requires about 5.8 GB of VRAM at 8 k context.
Does the model support image input?
Yes, the model is fully multimodal and accepts text, image, and video inputs.
What license applies to this model?
The model is released under the Apache‑2.0 license, requiring attribution.