whatmodel.sh / Jamba Large 1.7
Jamba Large 1.7
↗ share
+ contribute
Jamba Large 1.7 is an open-weights language model from AI21 Labs, released July 2025. Its published size is 398B parameters (94B active per token) and a 256k-token context window. Licence: jamba-open-model-license.
Catalogue identity notes
AI21 docs (observed 2026-10-09): 'jamba-large currently points to jamba-large-1.7-2025-07' and 'jamba-large-1.7 points to jamba-large-1.7-2025-07'. Weights ai21labs/AI21-Jamba-Large-1.7 @f95d1c3 (created 2025-07-02, licence other: jamba-open-model-license, gated). Vectara row label 'ai21labs/jamba-large-1.7-2025-07' is that exact dated API snapshot.
Model information sources
Release date ↗ · Weights licence ↗
AI21 docs Model Details: 'Jamba Large 398B parameters (94B active) 256K 1.7 2025-07'; HF safetensors metadata 398,555,145,696 (BF16).
$ how it compares
The LLMs ranked either side of Jamba Large 1.7, out of 1132 with a score, then more from AI21 Labs.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 562 |  Mistral-NeMo-Minitron 8B Instruct | 50±8 | local | ||
| 563 |  Gemini 1.5 Flash (001) | 50±1 | comparison only | ||
| 564 | Jamba Large 1.7 | 50±15 | api price unknown +local | ||
| 565 |  Llama-3-8B-ProLong-512k-Instruct | 50±5 | local | ||
| 566 |  EXAONE 3.5 7.8B Instruct | 50±4 | local | ||
| more from AI21 Labs | |||||
| 332 | Jamba 1.6 Large | 58±11 | local | ||
| 485 | Jamba 1.6 Mini | 53±10 | local | ||
| 526 | Jamba2 Mini | 52±15 | api price unknown +local | ||
$ what it's good at
other tests1 not in a task · 1.0% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Vectara hallucination leaderboard (HHEM-2.3, factual consistency rate) | 90.3% ✎ | ▁▂▁▂▅█▂▃▄▃▁▁ beats 46/98 | 1.0% |
$ where to run it
Through an API
api · price unknown · 256k context · docs.ai21.com ↗
llama.cpp · recommended
version
- Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.macOS / Linux
curl -LsSf https://llama.app/install.sh | shWindowsirm https://llama.app/install.ps1 | iex - Run Jamba Large 1.7 · needs ~240.4 GB · from huggingface.co/bartowskichat in the terminal
llama cli -hf bartowski/ai21labs_AI21-Jamba-Large-1.7-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf bartowski/ai21labs_AI21-Jamba-Large-1.7-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Jamba Large 1.7 · needs ~240.4 GB · from huggingface.co/bartowski
- Or download it in the terminal
lms get https://huggingface.co/bartowski/ai21labs_AI21-Jamba-Large-1.7-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Other ways to run it
- Run it as published · needs ~797.11 GB, NVIDIA only · from huggingface.co/ai21labs (official)
vllm serve ai21labs/AI21-Jamba-Large-1.7 --tensor-parallel-size 8 --quantization experts_int8
Official weights and documentation: huggingface.co/ai21labs ↗
$ how the score was worked out · Vectara hallucination leaderb… 1%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 1 | 1% |
| prior · pull toward the middle | 99% | |
| weighted average | = 50.2 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json