Minitron 8B Base needs about 6.5 GB of memory at Q4_K_S (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 17 quants, from 3.6 GB (Q2_K) to 16.6 GB.
Minitron 8B Base – 8.27B parameter transformer decoder
Minitron 8B Base is a pruned and distilled version of Nemotron‑4 15B. It contains 8.27B parameters and supports a 4096 token context. The model is released under the NVIDIA Open Model License and is intended for research and development.
Good at
- Text generation with 4096 token context
- Multilingual and code understanding
- Efficient inference with low‑bit quantization
Limits
- No vision support
- Requires 8.27B parameters – large memory footprint
- License is NVIDIA Open Model License
Best for
- Research prototyping
- Fine‑tuning on custom text corpora
- Low‑latency inference on GPUs with 8‑bit quantization
Who it’s for. Researchers and developers who need a compact 8B transformer for text tasks. The model is suitable for experimentation and fine‑tuning but is not intended for production deployment without further validation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.6 GB | 4.6 GB | Fits | Get file → | |
| IQ3_XS | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_S | 4.0 GB | 5.0 GB | Fits | Get file → | |
| IQ3_S | 4.0 GB | 5.0 GB | Fits | Get file → | |
| IQ3_M | 4.1 GB | 5.2 GB | Fits | Get file → | |
| Q3_K | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_L | 4.8 GB | 5.8 GB | Fits | Get file → | |
| IQ4_XS | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_S | 5.0 GB | 6.0 GB | Fits | Get file → | |
| IQ4_NL | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q4_K | 5.2 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_S | 5.8 GB | 6.9 GB | Fits | Get file → | |
| Q5_K | 6.0 GB | 7.0 GB | Fits | Get file → | |
| Q6_K | 6.8 GB | 7.8 GB | Tight | Get file → | |
| Q8_0 | 8.8 GB | 9.8 GB | Too big | Get file → | |
| BF16 | 16.6 GB | 17.6 GB | Too big | Get file → | |
| — | 16.6 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (file size 4.97 GB, estimated 6.5 GB memory). For 12 GB VRAM, Q5_K_S (5.83 GB, 7.4 GB memory) offers a good balance. For 16 GB VRAM, Q6_K (6.79 GB, 8.4 GB memory) provides higher precision.
What GPU do you need for Minitron 8B Base?
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 Q3_K (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K (6.0 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.6 GB file, about 18.1 GB in use).
Which Minitron 8B Base quant should you choose?
Q4_K_S (5.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q2_K at 3.6 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Minitron 8B Base
How much VRAM does Minitron 8B Base need?
About 6.5 GB at Q4_K_S with an 8K context window. That is the 5.0 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 Minitron 8B Base on an 8 GB GPU?
Yes, with Q5_K: the 6.0 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Minitron 8B Base GGUF?
It depends on the quant: Q2_K is 3.6 GB, IQ3_XS is 3.9 GB, Q3_K_S is 4.0 GB, IQ3_S is 4.0 GB, IQ3_M is 4.1 GB, Q3_K is 4.4 GB and 11 more.
What context length does Minitron 8B Base support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.
Where can I download Minitron 8B Base GGUF?
The files are on Hugging Face in the legraphista/Minitron-8B-Base-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 Minitron 8B Base use?
Hugging Face lists the license as other. 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 Minitron 8B Base on 8 GB VRAM?
Yes, using Q4_K_S quantization the estimated memory usage is 6.5 GB at 8K context, which fits within 8 GB VRAM.
Does the model support image input?
No, the model only accepts text input.
What license applies to this model?
The model is released under the NVIDIA Open Model License Agreement.