Jamba Large 1.7
AI21 · released Jul 2, 2025 · ai21labs/AI21-Jamba-Large-1.7
- Type
- Open weightsCustom licence
- Params
- 399B
- Context
- 256K
about 192K words of context · download allowed, licence restricts use
Our take
The case for it
- A 256,000-token request capacity means a long report or a stack of files goes in without being split up first, though reliable recall across all of it is unverified in our data.
- You can download it and run it yourself, which keeps the work on your own hardware; the custom licence puts conditions on commercial use and redistribution, so it needs reading before you build on it.
The case against it
- Near the bottom of every preference board we hold: 152nd of 168 on Arena Text (overall) as of 25 Sep 2026, and 152nd of 168 on Arena Coding as of 25 Sep 2026. These boards record which answer people preferred, not whether it was correct.
- The custom licence puts conditions on commercial use and redistribution, so it needs reading before you build on it.
- At 399 billion parameters this is hardware sized for a datacentre rather than a workstation, so running it yourself is a serious commitment.
How good is it?
An open text model for general chat, though it trails most models on everyday questions, writing and code.
- getting answers to everyday questionsArena Text (overall) · 152nd of 168
- drafts, rewrites and editingArena Creative Writing · 146th of 168
- writing and completing codeArena Coding · 152nd of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)152nd of 168 · 1289
CodingWriting and fixing code on its own
Arena Coding152nd of 168 · 1312
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing146th of 168 · 1261
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model6 scoresEvery figure we hold, from 6 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 123.2 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 43 days ago — each listing carries its own date.
- per 1M tokens
- $2.00 in / $8.00 out
- Context served
- 256K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.00 / $8.00checked 43 days ago | 256K | not measured | Unknown | Unknown | Unknown |
| AI21fp8Through OpenRouter | $2.00 / $8.00checked 43 days ago | 256K | not measured | Unknown | Unknown | Unknown |
Across the 2 listings we hold: 0 say they do not train on prompts, 0 say they do and 2 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✗ |
| AI21fp8Through OpenRouter | ✓ | ✓ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- ai21labs/AI21-Jamba-Large-1.7
- Takes in, gives back
- Text in, text out
- Catalogue slug
- ai21-jamba-large-1-7