JA

AI21 Jamba2 Mini

JambaGGUF by bartowskiUpdated 2026-01-08
Download on Hugging Face
Parameters51.6B
Context256K
Layers32
Architecturejamba
Smallest quant0.0 GB
Quick answer

AI21 Jamba2 Mini needs about 36.0 GB of memory at Q4_K_M (a 31.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 29 quants, from 0.0 GB to 103.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

AI21 Jamba2 Mini – 51.6B parameter open‑source LLM

AI21 Jamba2 Mini is a 51.6B parameter model built on the Jamba architecture. It offers a 256K context window and is optimized for enterprise reliability and steerability. The model is released under Apache‑2.0 and supports a wide range of quantizations for llama.cpp.

Good at

  • High‑throughput instruction following
  • Large context handling
  • Enterprise‑grade reliability

Limits

  • Requires large VRAM for full precision
  • No vision support
  • Context limited to 256K tokens

Best for

  • Enterprise chatbots
  • Technical documentation summarization
  • Grounded Q&A systems

Who it’s for. Developers and data scientists building production agents that need reliable, grounded responses. The model is suitable for commercial use under the Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 4.8 GB
Fits Get file →
IQ1_M11.2 GB 16.0 GB
Too big Get file →
IQ2_XXS12.5 GB 17.3 GB
Too big Get file →
IQ2_XS14.3 GB 19.1 GB
Too big Get file →
IQ2_S14.4 GB 19.2 GB
Too big Get file →
IQ2_M16.2 GB 21.0 GB
Too big Get file →
Q2_K18.0 GB 22.8 GB
Too big Get file →
Q2_K_L18.2 GB 23.0 GB
Too big Get file →
IQ3_XXS20.2 GB 25.0 GB
Too big Get file →
IQ3_XS21.2 GB 26.0 GB
Too big Get file →
Q3_K_S22.3 GB 27.1 GB
Too big Get file →
IQ3_M23.3 GB 28.1 GB
Too big Get file →
Q3_K_M23.5 GB 28.2 GB
Too big Get file →
Q3_K_L24.5 GB 29.3 GB
Too big Get file →
Q3_K_XL24.7 GB 29.5 GB
Too big Get file →
IQ4_XS27.5 GB 32.3 GB
Too big Get file →
IQ4_NL29.1 GB 33.9 GB
Too big Get file →
Q4_029.6 GB 34.4 GB
Too big Get file →
Q4_K_S30.1 GB 34.9 GB
Too big Get file →
Q4_K_M31.2 GB 36.0 GB
Too big Get file →
Q4_K_L31.4 GB 36.2 GB
Too big Get file →
Q4_132.3 GB 37.1 GB
Too big Get file →
Q5_K_S35.5 GB 40.3 GB
Too big Get file →
Q5_K_M36.6 GB 41.4 GB
Too big Get file →
Q5_K_L36.7 GB 41.5 GB
Too big Get file →
Q6_K42.3 GB 47.1 GB
Too big Get file →
Q6_K_L42.5 GB 47.3 GB
Too big Get file →
Q8_054.8 GB (2 parts) 59.6 GB
Too big Get file →
BF16103.2 GB (3 parts) 108.0 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (12.48 GB file, 17.3 GB memory at 8 k context). For 12 GB VRAM, IQ3_XS (21.19 GB file, 26 GB memory). For 16 GB VRAM, Q4_K_M (31.18 GB file, 36 GB memory).

What GPU do you need for AI21 Jamba2 Mini?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ1_M (11.2 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q2_K_L (18.2 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_XL (24.7 GB file, about 29.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K_L (42.5 GB file, about 47.3 GB in use).

Which AI21 Jamba2 Mini quant should you choose?

Q4_K_M is the usual starting point for AI21 Jamba2 Mini: it balances file size and quality well. Here it is a 31.2 GB file.

The Q8_0 file is 54.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturejamba
Parameters51.6B (approximate, mixture of experts)
Layers32
Trained context262,144 tokens
KV cache (fp16)512 KB per token

Source

Quantized bybartowski
FamilyJamba
Licenseapache-2.0
Downloads (HF)1,328
Last updated2026-01-08

Frequently asked questions about AI21 Jamba2 Mini

How much VRAM does AI21 Jamba2 Mini need?

About 36.0 GB at Q4_K_M with an 8K context window. That is the 31.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run AI21 Jamba2 Mini on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AI21 Jamba2 Mini GGUF?

It depends on the quant: file is 0.0 GB, IQ1_M is 11.2 GB, IQ2_XXS is 12.5 GB, IQ2_XS is 14.3 GB, IQ2_S is 14.4 GB, IQ2_M is 16.2 GB and 23 more.

What context length does AI21 Jamba2 Mini support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download AI21 Jamba2 Mini GGUF?

The files are on Hugging Face in the bartowski/ai21labs_AI21-Jamba2-Mini-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does AI21 Jamba2 Mini use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run AI21 Jamba2 Mini on 8 GB VRAM?

Use the IQ2_XXS quant, which requires about 17.3 GB memory at 8 k context. It will fit within 8 GB VRAM with efficient batching.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing commercial use.

Other GGUFs of AI21-Jamba2-Mini

Similar models

Browse all →

More from bartowski

All by bartowski →

More Jamba models

All Jamba →

Other large models

All large models →