Jebadiah 9b v2 needs about 7.4 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 5.8 GB (Q4_K_M) to 9.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
Jebadiah 9B v2 – a decision‑only model for typed questions
Jebadiah 9B v2 is a 9‑billion‑parameter decision model based on Qwen3.5 architecture. It answers typed questions—choice, noul, or score—by returning probabilities, not generating text. The model is released under Apache‑2.0 and is available in GGUF format for llama.cpp, Ollama and LM Studio.
Good at
- Typed decision answering
- Fast inference on 8‑k context
- Compatible with System One API
Limits
- No text generation support
- Requires 8‑k context for memory estimates
- No vision capabilities
Best for
- Decision‑making workflows
- TypeSafe API integration
- Rapid inference on GPUs
Who it’s for. Developers building decision engines or integrating a probability‑based answer layer into existing systems. The model is suitable for applications that need quick, deterministic responses without text generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.8 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 6.6 GB | 8.2 GB | Too big | Get file → | |
| Q8_0 | 9.8 GB | 11.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.78 GB, ~7.4 GB RAM at 8 k context). If 12 GB VRAM is available, Q5_K_M (6.64 GB, ~8.2 GB RAM) offers higher precision. Q8_0 (9.79 GB, ~11.4 GB RAM) is recommended only for machines with 16 GB or more VRAM.
What GPU do you need for Jebadiah 9b v2?
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 Q4_K_M (5.8 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).
Which Jebadiah 9b v2 quant should you choose?
Q4_K_M is the usual starting point for Jebadiah 9b v2: it balances file size and quality well. Here it is a 5.8 GB file.
The Q8_0 file is 9.8 GB, about 1.7 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 Jebadiah 9b v2
How much VRAM does Jebadiah 9b v2 need?
About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.8 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 Jebadiah 9b v2 on an 8 GB GPU?
Yes, with Q4_K_M: the 5.8 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Jebadiah 9b v2 GGUF?
It depends on the quant: Q4_K_M is 5.8 GB, Q5_K_M is 6.6 GB, Q8_0 is 9.8 GB.
What context length does Jebadiah 9b v2 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 4.4 GB at 32K.
Where can I download Jebadiah 9b v2 GGUF?
The files are on Hugging Face in the frontier-infra/jebadiah-9b-v2-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 Jebadiah 9b v2 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 Jebadiah 9B v2 on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 7.4 GB RAM at 8 k context, fitting within 8 GB VRAM with some headroom.
Does Jebadiah 9B v2 support text generation?
No, it is a decision model that returns probabilities for typed questions only.