Up to date
microsoft MIT out 12 months ago
8.29B parameters, images and text in, text out, 125K tokens of context.
Verified 2026-10-25 Rank #670 in LLMs · score 72.8 method v1 Sources 3 Downloads 30d 2.6k · #573 of 619 tracked
Picked by rule from 2 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Fara-7B is a 7 billion parameter model that achieves a 73.5% success rate on the WebVoyager benchmark.
Microsoft released Fara1.5, a family of native computer use agent models at three scales built on Qwen3.5.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 18 quantized builds and 5 Spaces.
Top Spaces running it: 2025-ai-timeline/2025-ai-timeline ♥ 21 · prithivMLmods/CUA-GUI-Operator ♥ 12 · HyperCluster/Fara-BrowserUse ♥ 5
Weights only, an estimate: leave room for the KV cache. Method
About 5.0 GB at INT4, 10 GB at FP8, 20 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2025-10-30), amber triangles are 2 dated articles (each links to it), grey ticks are repo commits.
22 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in LLMs
| Pipeline tag | image-text-to-text |
|---|---|
| Library | transformers |
| Architectures | Qwen2_5_VLForConditionalGeneration |
| Model type | qwen2_5_vl |
| Dtype | bfloat16 |
| Params by dtype | BF16: 8,292,166,656 |
| Size band | M |
| MoE | no |
| Context length | 128,000 (config.json max_position_embeddings) |
| Languages | en |
| Papers | arXiv:2511.19663 |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · Qwen2_5_VLForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen2_5_VLForConditionalGeneration · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for Fara-7B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 20 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 10 GB · Single GPU (<24 GB) |
| INT4 (0.5 bytes/param) | 5.0 GB · Single GPU (<24 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
quantized: 18finetune: 3merge: 1
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| bartowski/microsoft_Fara-7B-GGUF | quantized | GGUF | — | — | mit | bartowski | 39 | 82.3k |
| gguf-org/fara-7b-gguf | quantized | gguf | — | — | mit | gguf-org | 5 | 17.2k |
| prithivMLmods/Fara-7B-AIO-GGUF | quantized | GGUF | — | — | mit | prithivMLmods | 3 | 13.8k |
| mradermacher/Fara-7B-i1-GGUF | quantized | GGUF | — | — | mit | mradermacher | 1 | 8.4k |
| mradermacher/Fara-7B-GGUF | quantized | GGUF | — | — | mit | mradermacher | 4 | 6.2k |
| XythicK/microsoft_Fara-7B-GGUF | quantized | GGUF | — | — | mit | XythicK | 0 | 4.3k |
| huihui-ai/Huihui-Fara-7B-abliterated | finetune | — | 8.29B | M | mit | huihui-ai | 12 | 1.9k |
| AlexKitipov/microsoft_Fara-7B-GGUF | quantized | GGUF | — | — | mit | AlexKitipov | 0 | 2.2k |
| batiai/Fara-7B-GGUF | quantized | GGUF | — | — | mit | batiai | 0 | 2k |
| microsoft/Fara-7B-onnx | quantized | — | — | — | mit | microsoft | 5 | 755 |
| yasserrmd/Fara-TARS-7B | merge | — | 8.29B | M | apache-2.0 | yasserrmd | 5 | 712 |
| AXONVERTEX-AI-RESEARCH/Fara-7B-Q8-GGUF | quantized | GGUF | — | — | mit | AXONVERTEX-AI-RESEARCH | 3 | 663 |
| josephmayo/Fara-7B-Abliterated-v2 | finetune | — | 8.29B | M | other | josephmayo | 0 | 262 |
| onnx-community/Fara-7B-Onnx | quantized | — | — | — | mit | onnx-community | 1 | 168 |
| Govlens/Fara-7B-Q8_0-GGUF | quantized | Q8_0 | — | — | mit | Govlens | 0 | 196 |
| mlx-community/Fara-7B-4bit | quantized | -4bit | 8.29B | M | mit | mlx-community | 0 | 154 |
| mlx-community/Fara-7B-8bit | quantized | -8bit | 8.29B | M | mit | mlx-community | 0 | 126 |
| Prince-1/Fara-7B-Onnx | quantized | — | — | — | mit | Prince-1 | 0 | 52 |
| developerjeremylive/Fara-7B-Onnx-etheroi | quantized | — | — | — | mit | developerjeremylive | 0 | 52 |
| handmadedigital/Fara-7B-UQFF | quantized | — | — | — | — | handmadedigital | 0 | 46 |
| cua-lite/Fara-7B | finetune | — | 8.29B | M | mit | cua-lite | 0 | 37 |
| suryatmodulus/Fara-7B-Onnx | quantized | — | — | — | mit | suryatmodulus | 0 | 36 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:40 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:12 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
