Elephant 1 needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 4.9 GB (Q3_K_L) to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Elephant 1 – 9B decision model with text and image inputs
Elephant 1 is a 9B‑parameter decision model based on Qwen3.5‑9B. It is fine‑tuned on 6.21M decision examples and supports text and image inputs. The model outputs calibrated probabilities for multiple choice, ordinal, and binary questions in a single pass.
Good at
- Decision classification
- Calibrated probability output
- Multi‑modal input
Limits
- No speculative decoding
- Requires CUDA GPU
- No vision encoder training
Best for
- Decision‑making workflows
- Routing tasks
- Guardrail enforcement
Who it’s for. Developers needing a lightweight decision model for classification, routing, or guardrail tasks. The model is MIT‑licensed and suitable for self‑hosting on a single CUDA GPU.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.0 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 8.9 GB | Too big | Get file → | |
| BF16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM use Q3_K_L (4.93 GB, 6.5 GB memory at 8k context). For 12 GB VRAM use Q4_K_M (5.63 GB, 7.2 GB memory). For 16 GB VRAM use Q5_K_M (6.47 GB, 8 GB memory).
What GPU do you need for Elephant 1?
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: the best quant that fits is Q5_K_M (6.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.4 GB file, about 8.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (7.4 GB file, about 8.9 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).
Which Elephant 1 quant should you choose?
Q4_K_M is the usual starting point for Elephant 1: it balances file size and quality well. Here it is a 5.6 GB file.
If memory is tight, the smallest file is Q3_K_L at 4.9 GB, with the quality trade-offs that come with fewer bits. 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 Elephant 1
How much VRAM does Elephant 1 need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Elephant 1 on an 8 GB GPU?
Yes, with Q5_K_M: the 6.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Elephant 1 GGUF?
It depends on the quant: Q3_K_L is 4.9 GB, Q4_K_M is 5.6 GB, Q5_K_M is 6.5 GB, Q6_K is 7.4 GB, BF16 is 17.9 GB.
What context length does Elephant 1 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Elephant 1 GGUF?
The files are on Hugging Face in the prithivMLmods/elephant-1-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 Elephant 1 use?
Hugging Face lists the license as mit. 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 Elephant 1 on 8 GB VRAM?
Yes, the Q3_K_L quantized file is 4.93 GB and requires about 6.5 GB memory at 8k context.
Does Elephant 1 support speculative decoding?
No, speculative decoding is not enabled for this model.