Fara 7B needs about 5.7 GB of memory at Q4_K_M (a 4.7 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 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Fara 7B – a compact multimodal computer‑use agent
Fara 7B is a 7.62 billion‑parameter multimodal decoder‑only model designed for computer use. It accepts a screenshot and text context, and outputs a chain‑of‑thought followed by a tool call. The model supports a 128 k token context length and is released under the MIT license.
Good at
- Vision‑enabled web‑automation
- High‑level goal planning
- Text‑based tool calling
Limits
- No vision support beyond screenshots
- Requires 128 k context for full performance
- No explicit language support list
Best for
- Automating web tasks like booking or shopping
- Generating tool‑call sequences for browsers
- Building lightweight agentic assistants
Who it’s for. Developers building computer‑use agents who need a small, vision‑enabled model. The model is suitable for research and production environments that can handle a 128 k context length and the provided quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q2_K | 3.0 GB | 4.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.1 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XS | 3.3 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 4.5 GB | Fits | Get file → | |
| Q2_K_L | 3.5 GB | 4.5 GB | Fits | Get file → | |
| IQ3_M | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q3_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_L | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ4_XS | 4.2 GB | 5.2 GB | Fits | Get file → | |
| IQ4_NL | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_0 | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_XL | 4.6 GB | 5.5 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 5.7 GB | Fits | Get file → | |
| Q4_1 | 4.9 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_L | 5.1 GB | 6.1 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_L | 5.8 GB | 6.8 GB | Fits | Get file → | |
| Q6_K | 6.3 GB | 7.2 GB | Tight | Get file → | |
| Q6_K_L | 6.5 GB | 7.5 GB | Tight | Get file → | |
| Q8_0 | 8.1 GB | 9.1 GB | Too big | Get file → | |
| BF16 | 15.2 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_M (3.8 GB) or Q2_K (4 GB). For 12 GB VRAM, Q3_K_S (4.5 GB) or Q3_K_M (4.8 GB) are good choices. For 16 GB VRAM, Q4_K_M (5.7 GB) or Q5_K_M (6.4 GB) provide higher quality. Estimates are approximate.
What GPU do you need for Fara 7B?
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 Q2_K (3.0 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K_L (6.5 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).
Which Fara 7B quant should you choose?
Q4_K_M is the usual starting point for Fara 7B: it balances file size and quality well. Here it is a 4.7 GB file.
The Q8_0 file is 8.1 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 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 Fara 7B
How much VRAM does Fara 7B need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 Fara 7B on an 8 GB GPU?
Yes, with Q6_K_L: the 6.5 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Fara 7B GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 2.8 GB, Q2_K is 3.0 GB, IQ3_XXS is 3.1 GB, IQ3_XS is 3.3 GB, Q3_K_S is 3.5 GB and 19 more.
What context length does Fara 7B support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download Fara 7B GGUF?
The files are on Hugging Face in the bartowski/microsoft_Fara-7B-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 Fara 7B 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 Fara 7B on 8 GB VRAM?
Yes, use the IQ2_M or Q2_K quantization, which require about 3.8–4 GB of VRAM at 8 k context.
Does Fara 7B support multiple languages?
The model has no explicit language list; it is trained on multilingual data but language support is not guaranteed.
What context length does Fara 7B need?
The model is trained with a 128 k token context length; using a smaller context may reduce performance.