AI21/Mixture of Experts

AJamba Large 1.6

Name: Jamba Large 1.6
Author: AI21

The AI21 Jamba 1.6 family of models is state-of-the-art, hybrid SSM-Transformer instruction following foundation models.

chatreasoningtool_usemultilingual

398B

Parameters (94B active)

256K

Context length

Benchmarks

Quantizations

Architecture

MoE

Released

2025-09-20

Layers

KV Heads

Head Dim

128

Family

jamba

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	118.9 GB	low
IQ2_M	2.93	146.3 GB	low
Q2_K	3.16	157.7 GB	low
IQ3_XXS	3.25	162.2 GB	low
IQ3_XS	3.5	174.6 GB	low
Q3_K_S	3.64	181.6 GB	low
IQ3_M	3.76	187.5 GB	low
Q3_K_M	4	199.5 GB	low
Q3_K_L	4.3	214.4 GB	moderate
IQ4_XS	4.46	222.4 GB	moderate
Q4_K_S	4.67	232.8 GB	moderate
Q4_K_M	4.89	243.8 GB	good
Q5_K_S	5.57	277.6 GB	good
Q5_K_M	5.7	284.1 GB	good
Q6_K	6.56	326.8 GB	excellent
Q8_0	8.5	423.4 GB	lossless
FP16	16	796.5 GB	lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN JAMBA LARGE 1.6 NOW

Rent on RunPod →Or Vast.ai →

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (1)

AA Intelligence11.0

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run jamba:398b-q4_K_M

Tag may need adjustment — check ollama.com/library/jamba for available tags.

▸ SETUP GUIDE

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more

Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

HuggingFace GGUF Downloads Build Hardware