jpt 4b needs about 4.3 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 2.3 GB (Q3_K_M) to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
JPT‑4B: fast, open multimodal decision model
JPT‑4B is a 4.21B parameter model built on Qwen3.5‑4B with a merged LoRA fine‑tune. It delivers calibrated probabilities for typed decisions in a single forward pass. The vision tower remains unchanged, enabling screenshots, photos, and video frames.
Good at
- Typed decision inference
- Single‑pass probability output
- Multimodal input support
Limits
- No reasoning tokens
- Limited to typed decision interface
- CC‑BY‑NC‑4.0 license
Best for
- Rapid decision support
- Structured question answering
- Multimodal analytics
Who it’s for. Developers needing low‑latency decision inference without generation. Researchers exploring calibrated probability outputs in multimodal contexts.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_M | 3.1 GB | 4.6 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (2.71 GB) or Q5_K_S (2.99 GB) are suitable, using about 4.3 GB or 4.6 GB of VRAM at 8 k context. For 12 GB VRAM, Q5_K_M (3.07 GB) or BF16 (8.42 GB) provide higher precision. Memory estimates are approximate.
What GPU do you need for jpt 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_L (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (3.1 GB file, about 4.6 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which jpt 4b quant should you choose?
Q4_K_M is the usual starting point for jpt 4b: it balances file size and quality well. Here it is a 2.7 GB file.
If memory is tight, the smallest file is Q3_K_M at 2.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about jpt 4b
How much VRAM does jpt 4b need?
About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.7 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 jpt 4b on an 8 GB GPU?
Yes, with Q5_K_M: the 3.1 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jpt 4b GGUF?
It depends on the quant: Q3_K_M is 2.3 GB, Q3_K_L is 2.4 GB, Q4_K_S is 2.6 GB, Q4_K_M is 2.7 GB, Q5_K_S is 3.0 GB, Q5_K_M is 3.1 GB and 1 more.
What context length does jpt 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 4.3 GB at 32K.
Where can I download jpt 4b GGUF?
The files are on Hugging Face in the prithivMLmods/jpt-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 jpt 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 JPT‑4B on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_S quantizations will fit within 8 GB VRAM, requiring roughly 4.3–4.6 GB at 8 k context.
Does JPT‑4B support vision tasks?
Yes, the unchanged vision tower allows processing of screenshots, photos, and video frames alongside text.
What license applies to JPT‑4B?
The model is released under CC‑BY‑NC‑4.0, allowing non‑commercial use with attribution.