Neutrino 0.6B Draft needs about 1.8 GB of memory at its main file (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Neutrino 0.6B Draft – a lightweight Qwen3 variant for fast decoding
Neutrino 0.6B Draft is a 596M‑parameter Qwen3 model in a single 327,719,836‑byte GGUF file. It is a speculative‑decoding draft for Neutrino‑8B, providing token‑identical output at higher speed. The model is not chat‑tuned and lacks instruction or tool use.
Good at
- Fast speculative decoding
- Low memory footprint
- Consistent token output with larger model
Limits
- No chat or instruction tuning
- No tool use support
- Context length limited to 40960 tokens
Best for
- Rapid prototyping of Qwen3 behavior
- Benchmarking speculative decoding
- Embedding in lightweight inference pipelines
Who it’s for. Developers needing a quick, low‑memory version of Neutrino‑8B for testing or deployment on modest hardware. It is suitable for research and experimentation rather than production chat services.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 1.8 GB | Fits | Get file → |
The only available quant is unknown, with a file size of 0.34 GB and estimated memory usage of 1.8 GB at 8 k context. This fits comfortably on systems with 4 GB or more VRAM. No alternative quants are provided.
What GPU do you need for Neutrino 0.6B Draft?
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 the main file (0.3 GB file, about 1.8 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Neutrino 0.6B Draft
How much VRAM does Neutrino 0.6B Draft need?
About 1.8 GB at its main file with an 8K context window. That is the 0.3 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 Neutrino 0.6B Draft on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Neutrino 0.6B Draft GGUF?
It depends on the quant: file is 0.3 GB.
What context length does Neutrino 0.6B Draft support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Neutrino 0.6B Draft GGUF?
The files are on Hugging Face in the FermionResearch/Neutrino-0.6B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Neutrino 0.6B Draft 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 Neutrino 0.6B Draft on 4 GB VRAM?
Yes, the model requires approximately 1.8 GB of VRAM at 8 k context, so 4 GB is sufficient.
Does this model support chat or instruction following?
No, it is not chat‑tuned and lacks instruction or tool use capabilities.
What is the context length of this model?
The model supports up to 40960 tokens of context.