jeff base needs about 1.6 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.7 GB (Q4_K_M) to 1.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Jeff v1.3: a small decision model based on Qwen3.5-0.8B
Jeff v1.3 is a 1.01 billion‑parameter decision model built on Qwen3.5-0.8B. It is designed to be used with LoRA adapters and returns calibrated probabilities for each option without generating text. The base alone performs modestly; adapters boost accuracy to over 90 %.
Good at
- Decision making with calibrated probabilities
- Fast inference with prefix caching
- Low‑memory deployment
Limits
- No chat or text generation
- Requires LoRA adapter for best performance
- Context limited to 262144 tokens
Best for
- Rapid decision pipelines
- A/B testing of options
- Embedded inference on edge devices
Who it’s for. Developers building decision‑making systems that need calibrated probabilities and low latency. The model is ideal for applications where text generation is unnecessary and adapters can be applied to specialize the base.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q8_0 | 1.1 GB | 2.0 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quantised file (0.67 GB) which requires about 1.6 GB of VRAM at 8 k context. For 12 GB VRAM, the Q8_0 file (1.08 GB) uses about 2 GB of VRAM. Both are suitable for low‑memory inference.
What GPU do you need for jeff base?
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: the best quant that fits is Q8_0 (1.1 GB file, about 2.0 GB in use).
Which jeff base quant should you choose?
Q4_K_M is the usual starting point for jeff base: it balances file size and quality well. Here it is a 0.7 GB file.
The Q8_0 file is 1.1 GB, about 1.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about jeff base
How much VRAM does jeff base need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.7 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 jeff base on an 8 GB GPU?
Yes, with Q8_0: the 1.1 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jeff base GGUF?
It depends on the quant: Q4_K_M is 0.7 GB, Q8_0 is 1.1 GB.
What context length does jeff base support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download jeff base GGUF?
The files are on Hugging Face in the mstrasser/jeff-base-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 jeff base 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 Jeff v1.3 on 8 GB VRAM?
Yes, the Q4_K_M quantised file fits in 8 GB VRAM and requires approximately 1.6 GB at 8 k context.
Does Jeff v1.3 support vision?
No, Jeff v1.3 is a text‑only decision model with no vision capabilities.
What license does Jeff v1.3 use?
Jeff v1.3 is released under the Apache‑2.0 license.