Fara1.5 9B needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 5.6 GB (Q4_K_M) to 9.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Fara1.5 9B – a 9B multimodal computer‑use agent for screenshot‑driven browser automation
Fara1.5 9B is a 9B parameter multimodal model that observes browsers through screenshots and emits structured tool calls. It is trained for end‑to‑end web task completion, using vision‑only perception and pixel‑level action grounding. The model supports a 262144‑token context and runs on a single high‑end GPU.
Good at
- End‑to‑end web task completion
- Vision‑only screenshot perception
- Pixel‑level click and drag grounding
Limits
- Requires screenshots, no DOM access
- No separate grounding model needed
- Runs only with MagenticLite or equivalent sandbox
Best for
- Browser automation tasks
- Form filling and reservations
- Trip planning and shopping carts
Who it’s for. Researchers and production teams that need a safe, on‑device computer‑use agent. The model is best deployed inside MagenticLite for sandboxing and domain allow‑lists.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
For an 8GB VRAM GPU, download the Q4_K_M file (5.63 GB) which uses about 7.2 GB of VRAM at 8k context. If more memory is available, the Q8_0 file (9.53 GB) uses about 11.1 GB of VRAM and offers higher precision.
What GPU do you need for Fara1.5 9B?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.6 GB file, about 7.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
Which Fara1.5 9B quant should you choose?
Q4_K_M is the usual starting point for Fara1.5 9B: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 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 Fara1.5 9B
How much VRAM does Fara1.5 9B need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 9B on an 8 GB GPU?
Yes, with Q4_K_M: the 5.6 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Fara1.5 9B GGUF?
It depends on the quant: Q4_K_M is 5.6 GB, Q8_0 is 9.5 GB.
What context length does Fara1.5 9B 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 9B GGUF?
The files are on Hugging Face in the Tdamre/Fara1.5-9B-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 9B 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 9B on an 8GB VRAM GPU?
Yes, the Q4_K_M quantization uses about 7.2 GB of VRAM at 8k context, fitting within an 8GB GPU. The Q8_0 quantization requires about 11.1 GB and will not fit.
Does Fara1.5 9B need a GPU to run?
The model is designed for GPU execution; it was validated on an RTX 4090 and requires a GPU with at least 8GB VRAM for the Q4_K_M quantization.
Is Fara1.5 9B safe for production use?
It includes critical‑point safety design that stops and asks before irreversible actions, but safe deployment requires sandboxing and domain allow‑lists as recommended by Microsoft.