---
type: "post"
id: "ifm-released-jais-3-six-arabic-centric-models-4b16cd"
slug: "ifm-released-jais-3-six-arabic-centric-models-4b16cd"
title: "IFM released Jais 3 , six Arabic-centric models from 0.9B to 375B parameters, all Apache 2.0."
description: "**Thesis:** Jais 3’s notable proposition is that an open Arabic model family can span edge devices to large server deployments while targeting agent workflows, not only conversational fluency."
retrieval_nugget: "**Thesis:** Jais 3’s notable proposition is that an open Arabic model family can span edge devices to large server deployments while targeting agent workflows, not only conversational fluency."
published_at: "2026-10-15"
updated_at: "2026-10-15"
record_date: "2026-10-15"
date_kind: "published_at"
topics: ["agent-workflows"]
source_urls: ["https://ifm.ai/blog/jais3"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:ifm-released-jais-3-six-arabic-centric-models-4b16cd"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:6a2f9f8bb03901133bc4be495f1f0c35b1289d7d99e211703c6fb9ccc0a82240","reviewed_at":"2026-10-15T13:04:54.915Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Jais 3’s notable proposition is that an open Arabic model family can span edge devices to large server deployments while targeting agent workflows, not only conversational fluency.","observed_facts":[{"text":"IFM says it is releasing six models from 0.9B to 375B parameters, with models and code under Apache 2.0.","source_urls":["https://ifm.ai/blog/jais3"]},{"text":"The smallest model is listed for phones and edge devices; the largest, 375B-A23B, is listed for an eight-H200 node.","source_urls":["https://ifm.ai/blog/jais3"]},{"text":"IFM says the family shares a training recipe and describes tool and MCP-server calls, terminal commands, web search, and Arabic document editing.","source_urls":["https://ifm.ai/blog/jais3"]}],"mechanism":"IFM says all six sizes share a training recipe and are adapted from K2 Horizon models of corresponding sizes, allowing teams to select deployment scale within a related Arabic-oriented family.","why_now":"The release puts Arabic language coverage, deployment choice, and agent capabilities in one package, so builders can evaluate a stack rather than a single chat endpoint.","implications":["teams building Arabic workflows can test whether a smaller local model handles their actual dialects and file tasks before assuming that the largest model is necessary.","The published weights, checkpoints, recipes, logs, and evaluation code make the release inspectable, but do not by themselves prove production reliability or cost-effectiveness."],"evidence_boundary":"Performance comparisons and claims that the 3.7B and 7B lead their size classes come from IFM’s own benchmark runs; the supplied source does not establish independent replication or production outcomes.","watch_conditions":["whether independent evaluations reproduce the reported agentic results on Arabic tasks and whether those results hold across dialects and real document workflows."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied for this specific Jais 3 release, so this creates a distinct record of its open model family, deployment range, and agent claims."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/ifm-released-jais-3-six-arabic-centric-models-4b16cd/","markdown":"https://newruntime.com/posts/ifm-released-jais-3-six-arabic-centric-models-4b16cd.md","json":"https://newruntime.com/posts/ifm-released-jais-3-six-arabic-centric-models-4b16cd.json"}
---

# IFM released Jais 3 , six Arabic-centric models from 0.9B to 375B parameters, all Apache 2.0.

## Retrieval answer

**Thesis:** Jais 3’s notable proposition is that an open Arabic model family can span edge devices to large server deployments while targeting agent workflows, not only conversational fluency.

**Thesis:** Jais 3’s notable proposition is that an open Arabic model family can span edge devices to large server deployments while targeting agent workflows, not only conversational fluency.

**Mechanism:** IFM says all six sizes share a training recipe and are adapted from K2 Horizon models of corresponding sizes, allowing teams to select deployment scale within a related Arabic-oriented family. This gives builders a choice between compact local deployment and larger server-scale models without leaving the same family. The release describes tool and MCP-server calls, terminal commands, web search, and editing Arabic PDFs, slides, and spreadsheets.

**Observed facts:** IFM says it is releasing six models from 0.9B to 375B parameters, with models and code under Apache 2.0. The smallest model is listed for phones and edge devices; the largest, 375B-A23B, is listed for an eight-H200 node. IFM also says it provides weights, checkpoints, some training data, recipes, logs, benchmarks, and evaluation code.

**Why now:** The release puts Arabic language coverage, deployment choice, and agent capabilities in one package, so builders can evaluate a stack rather than a single chat endpoint.

**First implication:** teams building Arabic workflows can test whether a smaller local model handles their actual dialects and file tasks before assuming that the largest model is necessary.

**Evidence boundary:** Performance comparisons and claims that the 3.7B and 7B lead their size classes come from IFM’s own benchmark runs; the supplied source does not establish independent replication or production outcomes.

**What to watch:** whether independent evaluations reproduce the reported agentic results on Arabic tasks and whether those results hold across dialects and real document workflows. The release is a capability and availability signal, not evidence that a particular deployment is reliable or cost-effective.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Workflows](https://newruntime.com/topics/agent-workflows.md): Explore the agent-workflows topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)