UmarTransit 1B needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.0 GB (Q4_K_M) to 1.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
UmarTransit 1B – a domain‑specific LLM for public transit and GTFS data
UmarTransit 1B is a 1.54 B‑parameter instruction‑tuned model based on Qwen2.5‑1.5B‑Instruct. It focuses on GTFS understanding, transit route analysis, and journey planning. The model is released under Apache‑2.0 and supports 32,768‑token context.
Good at
- GTFS validation and analysis
- Transit route and schedule queries
- Journey planning logic
Limits
- English only – no multilingual support
- Static schedule data – no real‑time predictions
- 1,024‑token context – limited for very long queries
Best for
- Transit agencies validating GTFS feeds
- Developers building transit route assistants
- Researchers studying transit network intelligence
Who it’s for. The model is intended for developers, transit agencies, and researchers working with public transit data. It is suitable for applications that require detailed GTFS knowledge and route analysis.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quantized file (0.99 GB, ~1.7 GB memory at 8K context). For 12 GB VRAM, the Q8_0 quantized file (1.65 GB, ~2.4 GB memory at 8K context) is suitable. Memory estimates are approximate.
What GPU do you need for UmarTransit 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: the best quant that fits is Q8_0 (1.6 GB file, about 2.4 GB in use).
Which UmarTransit 1B quant should you choose?
Q4_K_M is the usual starting point for UmarTransit 1B: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about UmarTransit 1B
How much VRAM does UmarTransit 1B need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 UmarTransit 1B on an 8 GB GPU?
Yes, with Q8_0: the 1.6 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of UmarTransit 1B GGUF?
It depends on the quant: Q4_K_M is 1.0 GB, Q8_0 is 1.6 GB.
What context length does UmarTransit 1B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download UmarTransit 1B GGUF?
The files are on Hugging Face in the umarfarookm/UmarTransit-1B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does UmarTransit 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 UmarTransit 1B on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 0.99 GB and requires about 1.7 GB of VRAM at 8K context.
Does the model support multiple languages?
No, it is English only and does not support multilingual inputs.
Can it provide real‑time transit predictions?
No, it only works with static schedule data and cannot compute real‑time routes.