Antares 1b needs about 4.3 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Antares 1b, 1.84B parameter LLM in Q4_K_M quant
Antares 1b is a 1.84B parameter model based on the granite architecture. It was converted to GGUF format by HolkViking and is available under the apache-2.0 license. The model supports a 131072 token context window.
Good at
- Large context handling
- Compact quantization
- Open source licensing
Limits
- No vision support
- Requires 4.3 GB VRAM at 8k context
- Single quant available
Best for
- Long-form text generation
- Context‑heavy summarization
- Research prototyping
Who it’s for. Developers and researchers needing a small, high‑capacity model that can run on consumer GPUs. The model is suitable for projects that require a 131072 token context window and can benefit from an open‑source license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.1 GB | 4.3 GB | Fits | Get file → |
The only available quant is Q4_K_M, 1.14 GB in size. It requires approximately 4.3 GB of VRAM at 8k context. For 8 GB VRAM setups this fits comfortably. For lower budgets, consider using a smaller context or swapping to CPU inference.
What GPU do you need for Antares 1b?
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 Q4_K_M (1.1 GB file, about 4.3 GB in use).
Which Antares 1b quant should you choose?
Q4_K_M is the usual starting point for Antares 1b: 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 Antares 1b
How much VRAM does Antares 1b need?
About 4.3 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 Antares 1b on an 8 GB GPU?
Yes, with Q4_K_M: the 1.1 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Antares 1b GGUF?
It depends on the quant: Q4_K_M is 1.1 GB.
What context length does Antares 1b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Antares 1b GGUF?
The files are on Hugging Face in the HolkViking/antares-1b-Q4_K_M-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 Antares 1b 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 on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 4.3 GB VRAM at 8k context, leaving headroom on an 8 GB GPU.
What is the maximum context length?
The model was trained with 131072 tokens and supports that full context length.
Is it allowed for commercial use?
Yes, the apache-2.0 license permits commercial use.