Jamba-Reasoning-3B needs about 4.8 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.9 GB (Q4_K_M) to 6.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.
Jamba-Reasoning-3B: 3.2B parameter reasoning model with long‑context support
Jamba-Reasoning-3B is a 3.2B parameter model optimized for efficient sequence processing. It combines Transformer attention with Mamba state‑space layers, enabling long‑context handling and fast inference on laptops and mobile GPUs.
Good at
- Long‑context reasoning
- Efficient sequence processing
- Tool usage
Limits
- No vision support
- Requires 8k context for memory estimates
- License is Apache-2.0
Best for
- Complex reasoning tasks
- Tool‑enabled workflows
- Long‑document analysis
Who it’s for. Developers needing a compact yet powerful reasoning model for edge devices. Ideal for applications that require long‑context understanding without heavy GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.9 GB | 4.8 GB | Fits | Get file → | |
| F16 | 6.4 GB | 9.3 GB | Too big | Get file → |
For 8GB VRAM, use Q4_K_M (file size 1.93GB, estimated memory 4.8GB at 8k context). For higher precision on 16GB VRAM, F16 (file size 6.4GB, estimated memory 9.3GB at 8k context) is suitable.
What GPU do you need for Jamba-Reasoning-3B?
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 Q4_K_M (1.9 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (1.9 GB file, about 4.8 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (6.4 GB file, about 9.3 GB in use).
Which Jamba-Reasoning-3B quant should you choose?
Q4_K_M is the usual starting point for Jamba-Reasoning-3B: it balances file size and quality well. Here it is a 1.9 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Jamba-Reasoning-3B
How much VRAM does Jamba-Reasoning-3B need?
About 4.8 GB at Q4_K_M with an 8K context window. That is the 1.9 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 Jamba-Reasoning-3B on an 8 GB GPU?
Yes, with Q4_K_M: the 1.9 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 Jamba-Reasoning-3B GGUF?
It depends on the quant: Q4_K_M is 1.9 GB, F16 is 6.4 GB.
What context length does Jamba-Reasoning-3B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.4 GB at 32K.
Where can I download Jamba-Reasoning-3B GGUF?
The files are on Hugging Face in the ai21labs/AI21-Jamba-Reasoning-3B-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 Jamba-Reasoning-3B 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 Jamba-Reasoning-3B on 8GB VRAM?
Yes, the Q4_K_M quantization uses about 4.8GB at 8k context, fitting within 8GB VRAM.
Does this model support vision tasks?
No, it has no vision capabilities.
What license does it use?
Apache-2.0.