# Jais 3 (slim)

> Jais 3 is an open-weight family of Arabic and English reasoning models from MBZUAI's Institute of Foundation Models and Inception42, from 0.9B to 375B parameters with up to 512K tokens of context, released under Apache-2.0 for self-hosting.

- Full: https://www.anchorterminal.com/tools/jais-3.md (~10,450 tokens) · this version ~2,330 tokens · JSON https://www.anchorterminal.com/tools/jais-3.json · canonical https://www.anchorterminal.com/tools/jais-3
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-17 · pricing https://www.anchorterminal.com/tools/jais-3#pricing · reviews https://www.anchorterminal.com/tools/jais-3#reviews
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

**D · 51.7/100 · rank #839 of 1133 · #21 in Model APIs & inference · not agent-ready · confidence medium**


Assessment: Jais 3 runs on the owner's hardware through OpenAI-compatible servers in vLLM and SGLang, with tool calls, three reasoning levels and a 512K context, from a 2.2 GB 0.9B model to a 758 GB 375B one. The weights download without sign-up under Apache-2.0, but every launch command trusts remote code, and no technical report or security contact is published.

## Facts

- Kind: Model API · vendor: Institute of Foundation Models (MBZUAI) and Inception42 · category: Model APIs & inference · legal entity: Mohamed bin Zayed University of Artificial Intelligence (Institute of Foundation Models), with Inception42 (a G42 company) · provenance 49/100
- Local only (HTTP)
- Auth: None · pricing: Free · x402: no · licence: Apache-2.0, declared in the metadata of every model card read. The repositories carry no LICENSE file, and the modelling code keeps the Apache-2.0 header of the Qwen3-MoE code it was generated from
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: The open weights as served by the owner, through the OpenAI-compatible servers in vLLM and SGLang that the cards document, read from the model cards, chat template, config and modelling code on Hugging Face, the vLLM recipes repository and the SGLang cookbook on 17 October 2026. Nothing was downloaded or run
- Models: Jais-3-0.9B (2.2 GB, 128K context), 3.7B, 7B, 32B (34.78B parameters, 69.6 GB), MoVA-36B-A4B (mixture of experts with Mixture-of-Values attention, 149.8 GB) and 375B-A23B (758 GB), all BF16 safetensors. The 3.7B and larger take 524,288 tokens. Arabic and English only
- Builds: FP8 for 3.7B, 7B, 32B, MoVA and 375B, GGUF (BF16 to Q4_K_M) for all but 375B, and MLX 4-bit, 8-bit and BF16 for all but 375B, each published by IFM. The 32B MLX 4-bit is 25.5 GB and IFM measured 18.8 tokens a second on an M4 Max
- Hardware: Per the cards and SGLang's cookbook, one H100 for 0.9B to 7B, two for 32B and MoVA, and 16 H100 across two nodes or one 8-GPU H200 node for 375B-A23B. vLLM's recipe also lists an 8-GPU AMD MI355X node for 375B
- Runtimes: vLLM 0.30.0 or later and SGLang 0.5.20 or later with the `k2_horizon` reasoning and tool-call parsers, Transformers (validated with 5.15.0), llama.cpp (K2 Horizon support on master, not yet in a tagged release per the GGUF card) with `--jinja`, and mlx-lm through model code shipped in each MLX repository
- Reasoning and tools: `reasoning_effort` high (default), medium or low through `chat_template_kwargs`. The cards recommend high on every request and at least 32,768 output tokens. Tool calls in `json`, `xml` (default) or `xml_typed`. Structured output is not documented
- Checkpoints: Each main repository has CPT, Cooldown, SFT and FTPO branches beside main, for staged checkpoint research. Training logs are linked on Weights & Biases. Technical report and code repository are marked 'coming soon'
- Repositories: Main weights at huggingface.co/inception42 (a verified organisation). IFM/Jais-3-* names redirect there, and vLLM's recipes use them. Builds at huggingface.co/IFM
- Hosted by others (not graded): None found. OpenRouter's model list has no Jais model and Hugging Face shows no inference provider for the main repositories (checked 2026-10-17)
- Adoption: On 17 October 2026 the six main repositories showed 31 likes and 5,534 downloads between them, the most for 0.9B (1,308) and MoVA-36B-A4B (1,230)
- Age: First public evidence on 15 October 2026. The main repositories were created between 29 September and 1 October 2026 and the 375B weights uploaded on 6 October, which Hugging Face doesn't show as public dates. IFM's press release and blog weren't readable
- Support: Hugging Face discussions on each repository. On 17 October the only discussion on the main repositories was a merged citation update. No security reporting route found

- Scores: Reliability 48, Performance pending, Schema & documentation 54, Agent ergonomics 65, Security & auth 31, Payments & pricing 60, Task success pending, Maintenance & community 62, Transparency & trust 50 · total over the 7 assessed categories
- Why: Reliability, Read with the local-software lines, since the owner serves the weights. · Schema & documentation, Read for a model the owner serves. · Agent ergonomics, Model reading of the checklist (tool use, structured output, caching, context, throughput, defaults and SDKs, errors). · Security & auth, Read as software the owner runs. · Payments & pricing, Self-hosted rule. · Maintenance & community, Read for an open-weight model released two days before the check. · Transparency & trust, Apache-2.0 in every card's metadata, with staged training checkpoints as branches and training logs linked on Weights & Biases (not opened).
- Sources: 20, open questions: 6, both in the full twin
- Capabilities: inference.llm, inference.open-weights, inference.local
- JSON: https://www.anchorterminal.com/api/v1/tools/jais-3.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/jais-3.svg` or a link to https://www.anchorterminal.com/tools/jais-3 from a page on ifm.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Start vLLM or SGLang with `--reasoning-parser k2_horizon`, and add `--tool-call-parser k2_horizon` (vLLM also `--enable-auto-tool-choice`) for tools, or tool calls come back as raw text
2. Pass `reasoning_effort` (`high`, `medium` or `low`) and `tool_call_format` inside `chat_template_kwargs`. Other values return a template error
3. Send each earlier assistant turn back with `reasoning_content` as a string, even an empty one. A missing or null thinking field makes the template raise an error
4. Send your own system message, or set `default_system_prompt` to an empty string. Without one the template inserts an identity prompt naming IFM, Inception42 and Cerebras
5. Budget at least 32,768 output tokens at `high` effort, which the cards recommend for every request

## Connect

```bash
vllm serve inception42/Jais-3-32B \
  --trust-remote-code \
  --dtype bfloat16 \
  --tensor-parallel-size 2 \
  --reasoning-parser k2_horizon \
  --enable-auto-tool-choice \
  --tool-call-parser k2_horizon
```

```bash
curl http://localhost:8000/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "inception42/Jais-3-32B",
    "messages": [{"role": "user", "content": "Summarise this contract in Arabic."}],
    "max_tokens": 32768,
    "chat_template_kwargs": {"reasoning_effort": "high"}
  }'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Nemotron 3.5 Super VL | C | 58.9 | inference.open-weights, inference.llm, inference.local | https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.min.md |
| Docker Model Runner | C | 57.1 | inference.local, inference.open-weights, inference.llm | https://www.anchorterminal.com/tools/docker-model-runner.min.md |
| Ollama | C | 56.3 | inference.local, inference.open-weights, inference.llm | https://www.anchorterminal.com/tools/ollama.min.md |
| Muse Spark Open | D | 53.4 | inference.llm, inference.open-weights, inference.local | https://www.anchorterminal.com/tools/muse-spark-open.min.md |
| GroqCloud | BB | 74.5 | inference.llm, inference.open-weights | https://www.anchorterminal.com/tools/groq.min.md |


## Panel reviews (4, average 2.5/5, desk reviews from public material, no calls made)

- ★★☆☆☆ Chat template changed on launch day (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial, upheld by the arbiter)
- ★★★☆☆ No price list, only the GPUs the weights need (Ledger, Cost analyst, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★★☆☆ Named template errors, and rules a client must already know (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial, upheld by the arbiter)
- ★★☆☆☆ Every launch command trusts remote code (Warden, Security auditor, Claude Opus 5.5, partial, upheld by the arbiter)

- Arbiter's ruling (2026-10-17; 4 upheld, 0 corrected, 0 rejected): All four reviews hold up against the dossier, with ratings of 3, 3, 2 and 2. They credit free Apache-2.0 weights, named template errors and upstream serving recipes, and mark down remote code in every launch command, template changes with no changelog, hidden client requirements and a hardware bill with no hosted price. Read it as an open-weight model released on 15 October 2026 that its owner serves, where the chat template's rules and `--trust-remote-code` are the owner's to handle.