An open-weight browser-action model family with screenshot-only perception and a caller-owned execution loop.
Computer-use modelopen source
Fara1.5 supplies the action model, with separate 4B, 9B and 27B checkpoints. Use the documented Fara/MagenticLite harness to execute browser actions; this is not a managed browser subscription. The 9B card is the detailed control-surface reference here.
Teams evaluating self-operated browser model weights
Experiments that can pin a checkpoint and Fara-compatible harness
LOOK ELSEWHERE WHEN
You need a turnkey hosted automation service
You require a proven security guarantee from trained pause behavior
Fit recommendations are editorial interpretations of the documented architecture.
Documented capabilities
CAPABILITY
DOCUMENTED STATE
SOURCE
model family
Fara1.5 comprises 4B, 9B and 27B browser-agent models based on Qwen3.5.
interaction
The agent uses recent screenshots and emits actions sequentially; permitted actions include browser control, search and user questions.
release history
The research article was released May 21, 2026; its July 22 update reports MIT-licensed weight availability.
exact model identity
Microsoft publishes separate Fara1.5-4B, Fara1.5-9B and Fara1.5-27B cards, each declaring MIT. These are exact 1.5 identities, not the older Fara-7B model.
weight inventory 9b
The 9B Files view lists four safetensors shards plus an index and configuration files. No model weights were downloaded or executed.
vision runtime 9b
The 9B card documents screenshot-only observations rather than DOM/accessibility input, a 262,144-token context, Qwen3.5-9B base, and a caller-executed browser loop with MagenticLite/Fara CLI guidance.
safety boundary
The card describes trained pause behavior and recommends sandbox/allowlist/oversight controls. Training claims do not prove enforced approval or security guarantees in every integration.
Environment, deployment & control
Environment
browser
Full
desktop
Unknown
mobile
Unknown
Deployment
cloud
Unknown
local
Unknown
self Hosted
Unknown
Extensibility
api
Unknown
sdk
Unknown
mcp
Unknown
bring Your Own Model
Unknown
Control method
screenshots
Full
mouse Keyboard
Full
dom Or Accessibility
Unknown
code Execution
Unknown
Unknown = insufficient public evidence; No evidence = an explicit negative record; N/A = does not apply to this layer.
Trust, oversight & limitations
Documented oversight
human Approval
Unknown
audit Logs
Unknown
sandboxing
Unknown
prompt Injection Defense
Unknown
credential Controls
Unknown
Know the boundary
The 27B WebVoyager figure conflicts across Microsoft sources; no score is imported.
Weights were not downloaded or executed by COMPUTER USE. 4B/27B file inventory and standalone license/dependency review remain incomplete.
Training for approval behavior is not enforcement; isolate the runtime and enforce consequential-action approval in code.
Current pricing is not sufficiently verified, or its 14-day review window has expired. Check the official provider before budgeting.
Evidence, scope & unresolved questions
Stack classification: L1. Verified means the cited source supports the statement; it does not mean COMPUTER USE independently tested the product.
conflicted
research.conflict
Exact 4B/9B/27B MIT-declared cards found; 9B four weight shard filenames visible. No weight download, execution or standalone-license/dependency audit. Use exact 1.5 card identity; keep 4B/27B weight inventories and operational validation unverified.
Conflicting or incompletely resolved evidence is not used as a numerical current value.
huggingface.co ↗ · Verified Sep 28, 2026 · Recheck every 30 days
conflicted
research.conflict
Microsoft research article in the original ledger says 88.6; exact model card says 89.3. No matching run/version explanation found. Preserve original result observation and new conflicting card; no score substitution or formal result.
Conflicting or incompletely resolved evidence is not used as a numerical current value.
huggingface.co ↗ · Verified Sep 28, 2026 · Recheck every 30 days
verified
status
Official current documentation and product sources identify Microsoft Fara1.5 in the scope described here; account access and operational readiness have not been independently tested.
Documented by the provider; not an independent execution, reliability or security test.