AI21 Jamba Mini 1.7 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 23 quants, from 10.5 GB (IQ1_S) to 42.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.
AI21 Jamba Mini 1.7 is a 51.6B-parameter Jamba model in GGUF format, quantized by mradermacher. Its trained context length is 256K tokens. The repository has 23 quant files, from 10.5 GB (IQ1_S) to 42.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 10.5 GB | 15.3 GB | Too big | Get file → | |
| IQ1_M | 11.7 GB | 16.5 GB | Too big | Get file → | |
| IQ2_XXS | 13.6 GB | 18.4 GB | Too big | Get file → | |
| IQ2_XS | 15.1 GB | 19.9 GB | Too big | Get file → | |
| IQ2_S | 15.4 GB | 20.2 GB | Too big | Get file → | |
| IQ2_M | 16.9 GB | 21.7 GB | Too big | Get file → | |
| Q2_K_S | 17.5 GB | 22.3 GB | Too big | Get file → | |
| Q2_K | 18.7 GB | 23.5 GB | Too big | Get file → | |
| IQ3_XXS | 19.9 GB | 24.7 GB | Too big | Get file → | |
| IQ3_XS | 21.2 GB | 26.0 GB | Too big | Get file → | |
| IQ3_S | 22.3 GB | 27.1 GB | Too big | Get file → | |
| Q3_K_S | 22.3 GB | 27.1 GB | Too big | Get file → | |
| IQ3_M | 22.6 GB | 27.4 GB | Too big | Get file → | |
| Q3_K_M | 24.5 GB | 29.3 GB | Too big | Get file → | |
| Q3_K_L | 26.4 GB | 31.2 GB | Too big | Get file → | |
| IQ4_XS | 27.5 GB | 32.3 GB | Too big | Get file → | |
| Q4_0 | 29.2 GB | 34.0 GB | Too big | Get file → | |
| Q4_K_S | 29.4 GB | 34.1 GB | Too big | Get file → | |
| Q4_K_M | 31.2 GB | 36.0 GB | Too big | Get file → | |
| Q4_1 | 32.3 GB | 37.1 GB | Too big | Get file → | |
| Q5_K_S | 35.5 GB | 40.3 GB | Too big | Get file → | |
| Q5_K_M | 36.6 GB | 41.4 GB | Too big | Get file → | |
| Q6_K | 42.3 GB | 47.1 GB | Too big | Get file → |
What GPU do you need for AI21 Jamba Mini 1.7?
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: the best quant that fits is IQ1_S (10.5 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q2_K (18.7 GB file, about 23.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q3_K_L (26.4 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (42.3 GB file, about 47.1 GB in use).
Which AI21 Jamba Mini 1.7 quant should you choose?
Q4_K_M is the usual starting point for AI21 Jamba Mini 1.7: it balances file size and quality well. Here it is a 31.2 GB file.
If memory is tight, the smallest file is IQ1_S at 10.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AI21 Jamba Mini 1.7
How much VRAM does AI21 Jamba Mini 1.7 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 Jamba Mini 1.7 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of AI21 Jamba Mini 1.7 GGUF?
It depends on the quant: IQ1_S is 10.5 GB, IQ1_M is 11.7 GB, IQ2_XXS is 13.6 GB, IQ2_XS is 15.1 GB, IQ2_S is 15.4 GB, IQ2_M is 16.9 GB and 17 more.
What context length does AI21 Jamba Mini 1.7 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 Jamba Mini 1.7 GGUF?
The files are on Hugging Face in the mradermacher/AI21-Jamba-Mini-1.7-i1-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 Jamba Mini 1.7 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.