whatmodel.sh / Jamba 1.6 Large

Jamba 1.6 Large

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Jamba 1.6 Large is an open-weights language model from AI21 Labs, released February 2025. Its published size is 398.56B parameters (94B active per token). Licence: other (jamba-open-model-license).

Catalogue identity notes

Maker repo ai21labs/AI21-Jamba-Large-1.6 @f75d35d: licence tag other (jamba-open-model-license). 398,555,145,696 parameters from the Hugging Face safetensors metadata; active 94B per token (same architecture size as Jamba Large (AI21 docs: 'Jamba Large 398B parameters (94B active)'; see catalogue jamba-large-1-7)). Released 2025-02: month the maker's Hugging Face repo was created (createdAt 2025-02-27). Gated repository (licence acceptance required on Hugging Face).

58.1±11.0#251 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Jamba 1.6 Large, out of 1132 with a score, then more from AI21 Labs.

#modelscorewhereRAMreleased
330Grok Code Fast 1 SpaceXAI (xAI)58±3comparison only2025-08
331DeepSeek R1 Distill Llama 70B DeepSeek58±1api $0.80/M +local~30GB2025-01
332Jamba 1.6 Large AI21 Labs58±11local~839GB2025-02
333Phi-4-reasoning 14B Microsoft58±1api $0.22/M +local~10GB2025-04
334Olmo 3 32B Think Ai258±1local~21GB2025-11
more from AI21 Labs
485Jamba 1.6 Mini AI21 Labs53±10local~34GB2025-02
526Jamba2 Mini AI21 Labs52±15api price unknown +local~32GB2026-01
560Jamba 1.5 Large AI21 Labs50±1local~839GB2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 46% of its score
testresultvs the others in its rundifficultycountswhy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)97.7% ✎▁▁▂▃▄▄█▆▃▂▂▁ beats 118/140very easy · avg 94%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%blunt · maxed out · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~797.11 GB · from huggingface.co/ai21labs (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='ai21labs/AI21-Jamba-Large-1.6', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/ai21labs ↗

$ how the score was worked out · Vectara hallucination leaderb… 46%

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

sourceresultsshare of the scorelicence
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%Apache-2.0
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%
weighted average= 58.1

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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