Fara1.5 4B needs about 4.5 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Fara1.5 4B – a vision‑only multimodal agent for web browsers
Fara1.5 4B is a 4 billion‑parameter multimodal model designed for end‑to‑end web task completion. It processes screenshots only, predicts pixel‑level actions, and tracks reasoning as text. The model supports a 262 k token context window and is released under the MIT license.
Good at
- Vision‑only web browsing
- Pixel‑grounded click and drag actions
- Long‑trajectory reasoning
Limits
- No DOM or accessibility tree input
- Requires MagenticLite or similar sandbox for safety
- Large context needs 262 k tokens
Best for
- Automating form filling and reservations
- End‑to‑end web task agents
- Browser‑based tool‑call workflows
Who it’s for. Developers building browser automation agents or research teams needing a vision‑only multimodal model. The model is suitable for on‑device deployment with a single GPU such as an A100/H100/B200.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ2_M | 1.8 GB | 3.4 GB | Fits | Get file → | |
| Q2_K | 2.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XXS | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q2_K_L | 2.2 GB | 3.8 GB | Fits | Get file → | |
| IQ3_XS | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_S | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ3_M | 2.4 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_M | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_L | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_NL | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_XL | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_S | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_1 | 2.9 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_M | 2.9 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_L | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_L | 3.5 GB | 5.0 GB | Fits | Get file → | |
| Q6_K | 3.7 GB | 5.3 GB | Fits | Get file → | |
| Q6_K_L | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (2.65 GB file, ~4.2 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (2.88 GB file, ~4.5 GB memory) or Q5_K_S (3.13 GB file, ~4.7 GB memory). For 16 GB VRAM, Q5_K_L (3.47 GB file, ~5 GB memory) or Q6_K (3.68 GB file, ~5.3 GB memory).
What GPU do you need for Fara1.5 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 (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K_L (3.8 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which Fara1.5 4B quant should you choose?
Q4_K_M is the usual starting point for Fara1.5 4B: it balances file size and quality well. Here it is a 2.9 GB file.
The Q8_0 file is 4.5 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Fara1.5 4B
How much VRAM does Fara1.5 4B need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 2.9 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 Fara1.5 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Fara1.5 4B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 1.8 GB, Q2_K is 2.1 GB, IQ3_XXS is 2.1 GB, Q2_K_L is 2.2 GB, IQ3_XS is 2.3 GB and 19 more.
What context length does Fara1.5 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 Fara1.5 4B GGUF?
The files are on Hugging Face in the bartowski/Fara1.5-4B-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 Fara1.5 4B use?
Hugging Face lists the license as mit. 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 Fara1.5 4B on 8 GB VRAM?
Yes, the Q4_0 quant uses about 4.2 GB of VRAM at 8 k context, leaving room for the screenshot history.
Does the model support text‑only input?
No, it is vision‑only at perception time and requires screenshots to function.
What safety controls are needed?
The model should be run inside MagenticLite or a similar sandbox that enforces domain allow‑lists and real‑time monitoring.