ai21labs_AI21 Jamba 1.5 Mini needs about 27.1 GB of memory at Q3_K_S (a 22.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 22.3 GB (Q3_K_S) to 31.9 GB (Q4_K_L). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.
ai21labs_AI21 Jamba 1.5 Mini is a 51.6B-parameter Labs model in GGUF format, quantized by leafspark. Its trained context length is 256K tokens. The repository has 2 quant files, from 22.3 GB (Q3_K_S) to 31.9 GB (Q4_K_L).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 22.3 GB | 27.1 GB | Too big | Get file → | |
| Q4_K_L | 31.9 GB | 36.7 GB | Too big | Get file → |
What GPU do you need for ai21labs_AI21 Jamba 1.5 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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q3_K_S (22.3 GB file, about 27.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_L (31.9 GB file, about 36.7 GB in use).
Which ai21labs_AI21 Jamba 1.5 Mini quant should you choose?
Q3_K_S (22.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ai21labs_AI21 Jamba 1.5 Mini
How much VRAM does ai21labs_AI21 Jamba 1.5 Mini need?
About 27.1 GB at Q3_K_S with an 8K context window. That is the 22.3 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 ai21labs_AI21 Jamba 1.5 Mini on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ai21labs_AI21 Jamba 1.5 Mini GGUF?
It depends on the quant: Q3_K_S is 22.3 GB, Q4_K_L is 31.9 GB.
What context length does ai21labs_AI21 Jamba 1.5 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 ai21labs_AI21 Jamba 1.5 Mini GGUF?
The files are on Hugging Face in the leafspark/Jamba-1.5-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 ai21labs_AI21 Jamba 1.5 Mini use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.