AI21 Labs - Mixture of experts - verified
Run AI21 Jamba Large 1.7 locally
AI21 Jamba Large 1.7 is a 398.6B mixture-of-experts (94B active) model from AI21 Labs with a 262K-token context window, released under Jamba Open Model License (commercial use is allowed with conditions set out in the license); the smallest listed download is 797.1 GB, the official BF16 weights.
Official weights: ai21labs/AI21-Jamba-Large-1.7
- Total params
- 398.6B
- Active params
- 94B
- Context
- 262K
- Smallest download
- 797.1 GB
Fits in
Smallest download at most 85% of memoryNone of the tiers here. The smallest listed download is 797.1 GB, more than 85% of 256 GB.
Downloads
The official weights and every quantization listed for this model, with file sizes from Hugging Face. No quantized build was found from the usual publishers.
| Download | Format | Size | Repo |
|---|---|---|---|
Official weightsSmallest listed | BF16 | 797.1 GB | ai21labs/AI21-Jamba-Large-1.7 |
GB is decimal: 1 GB = 10^9 bytes. Add memory for the context and the operating system on top of the file size.
Run it
The official pages read for this directory publish no copyable run command for AI21 Jamba Large 1.7. Download the weights from ai21labs/AI21-Jamba-Large-1.7 and follow the model card's serving instructions.
Not sure which runtime to use? Compare local LLM runtimes by platform, API and features.
License
- License
- Jamba Open Model License
other - Commercial use
- Commercial use: ConditionsCommercial use is allowed with conditions set out in the license.
- Gated download
- Yes. Hugging Face asks you to accept the terms before downloading.
Worth knowing
The card says it does not fit on a single node of 8x 80GB GPUs at BF16, so AI21 recommends its ExpertsInt8 quantization in vLLM to serve up to about 220K tokens on that node.
Released (Hugging Face repo creation date).
FAQ
How big is the AI21 Jamba Large 1.7 download?
The official BF16 weights in ai21labs/AI21-Jamba-Large-1.7 are 797.1 GB. No smaller quantization is listed. Plan for more memory than the file size: the context (KV cache) and the operating system need room too.
Can I use AI21 Jamba Large 1.7 commercially?
AI21 Jamba Large 1.7 is released under Jamba Open Model License, and commercial use is allowed with conditions set out in the license. The Hugging Face download is gated: you accept the license terms before it starts. The license text is at https://huggingface.co/ai21labs/AI21-Jamba-Large-1.7/blob/main/LICENSE.txt.
How much memory do I need for AI21 Jamba Large 1.7?
Its smallest listed download is 797.1 GB, more than 85% of 256 GB, so it needs a multi-GPU server or a machine with more memory than the largest tier here.
What is the context length of AI21 Jamba Large 1.7?
262,144 tokens. A longer context needs more memory for the KV cache, so you can run with a shorter one when memory is tight.
Sources
Last verified from the pages below.
- HF API (params, license, createdAt) - huggingface.co
- HF file tree - huggingface.co
- Model card (model page) - huggingface.co
- Ollama search (no official library entry) - ollama.com
Newsletter
New open weights, every week
One email per week. New model releases, open-weight drops and what they mean for what you build.
Keep exploring
Best local AI models
Our curated picks by hardware tier, with benchmarks and the reasoning.
Model API pricing and specs
First-party prices per 1M tokens when you would rather call an API.
AI benchmark leaderboards
Sourced scores, for when you need to compare quality.
Setup guides
Point your coding tools at the model you picked.