Nova-1.2-0.8B needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.5 GB (Q2_K) to 2.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Nova-1.2-0.8B – a tool‑use focused Qwen‑35 model
Nova-1.2-0.8B is a 1.01B‑parameter model built on the Qwen‑35 architecture. It is tuned with a LoRA adapter for deterministic tool‑use and supports reasoning, tools, and vision. The model is released under the apache‑2.0 license.
Good at
- Tool‑use with JSON, XML, plain text
- Reasoning tasks
- Vision queries
Limits
- No vision support in some builds
- Large context requires high VRAM
- No multi‑modal beyond vision
Best for
- Chatbots that call external APIs
- Automated data extraction
- Interactive educational assistants
Who it’s for. Developers building applications that need reliable function calling and basic vision. The model is suitable for projects that require deterministic tool usage and can run on consumer GPUs with 8 GB or more VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_L | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ4_XS | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.8 GB | 1.8 GB | Fits | Get file → | |
| Q8_0 | 1.1 GB | 2.0 GB | Fits | Get file → | |
| F16 | 2.0 GB | 2.9 GB | Fits | Get file → |
For 8 GB VRAM use Q2_K (0.51 GB, 1.4 GB memory at 8k context). If more memory is available, Q3_K_S (0.54 GB, 1.5 GB) or Q4_K_M (0.67 GB, 1.6 GB) offer higher quality. Full precision F16 requires 2.03 GB and 2.9 GB memory.
What GPU do you need for Nova-1.2-0.8B?
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 F16 (2.0 GB file, about 2.9 GB in use).
Which Nova-1.2-0.8B quant should you choose?
Q4_K_M is the usual starting point for Nova-1.2-0.8B: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.1 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 0.5 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 Nova-1.2-0.8B
How much VRAM does Nova-1.2-0.8B need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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 Nova-1.2-0.8B on an 8 GB GPU?
Yes, with F16: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nova-1.2-0.8B GGUF?
It depends on the quant: Q2_K is 0.5 GB, Q3_K_S is 0.5 GB, Q3_K_M is 0.6 GB, Q3_K_L is 0.6 GB, IQ4_XS is 0.6 GB, Q4_K_S is 0.6 GB and 6 more.
What context length does Nova-1.2-0.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.
Where can I download Nova-1.2-0.8B GGUF?
The files are on Hugging Face in the mradermacher/Nova-1.2-0.8B-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 Nova-1.2-0.8B 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 Nova-1.2-0.8B on 8 GB VRAM?
Yes, the Q2_K quant uses 1.4 GB memory at 8k context, fitting within 8 GB VRAM.
Does Nova-1.2 support vision?
Yes, the model has detected vision ability, but it may require a separate vision backend.
Is tool use built into the model?
Yes, a LoRA adapter trained on ToolUse.1 is merged, enabling deterministic function calling.