Lodestar 4B needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.0 GB (Q2_K) to 8.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
Lodestar 4B – a 4.33B‑parameter vision‑enabled decision model
Lodestar 4B is a 4.33B‑parameter model based on StartLux‑Decision‑v1‑4B. It supports vision inputs and can process up to 262,144 tokens. The model is released under a cc‑by‑nc‑4.0 license.
Good at
- Vision‑enabled decision making
- Long‑context reasoning up to 262,144 tokens
- Fast inference with llama.cpp
Limits
- No open‑source license for commercial use
- Requires at least 3.6 GB VRAM for Q2_K at 8 k context
- Vision support only, no audio or text‑only specializations
Best for
- Image‑based question answering
- Decision‑making workflows with long text
- Batch inference on GPU
Who it’s for. Developers building decision systems that need to process images and large text contexts. The model is suitable for research and non‑commercial projects that can comply with the cc‑by‑nc‑4.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.6 GB | 6.2 GB | Fits | Get file → | |
| F16 | 8.7 GB | 10.3 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (file size 2.78 GB, estimated 4.4 GB memory) is a good balance. If 4 GB VRAM is available, Q3_K_M (2.32 GB, 3.9 GB memory) works. For the lowest memory use, Q2_K (1.96 GB, 3.6 GB memory) is recommended.
What GPU do you need for Lodestar 4B?
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 Q3_K_M (2.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.2 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.7 GB file, about 10.3 GB in use).
Which Lodestar 4B quant should you choose?
Q4_K_M is the usual starting point for Lodestar 4B: it balances file size and quality well. Here it is a 2.8 GB file.
The Q8_0 file is 4.6 GB, about 1.7 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 2.0 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 Lodestar 4B
How much VRAM does Lodestar 4B need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Lodestar 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Lodestar 4B GGUF?
It depends on the quant: Q2_K is 2.0 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.5 GB, IQ4_XS is 2.6 GB, Q4_K_S is 2.6 GB and 6 more.
What context length does Lodestar 4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.
Where can I download Lodestar 4B GGUF?
The files are on Hugging Face in the mradermacher/Lodestar-4B-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 Lodestar 4B use?
Hugging Face lists the license as cc-by-nc-4.0. 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 Lodestar 4B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 4.4 GB VRAM at 8 k context, which fits within 8 GB.
Does the model support text only inputs?
The model includes a vision tower and is designed for image‑based decision tasks, but it can also process text states.
What license applies to Lodestar 4B?
The model is released under a cc‑by‑nc‑4.0 license, allowing non‑commercial use with attribution.