JE

Jebadiah 4b v2

JebadiahGGUF by frontier-infraUpdated 2026-10-16
Download on Hugging Face
Parameters4.33B
Context256K
Layers33
Architectureqwen35
Smallest quant2.8 GB
Quick answer

Jebadiah 4b v2 needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.8 GB (Q4_K_M) to 4.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Jebadiah 4B v2 – a lightweight decision model for typed questions

Jebadiah 4B v2 is a 4.33 billion‑parameter decision model built on the Qwen35 architecture. It answers typed questions—choice, noul, or score—by returning probabilities for each option in a single forward pass. The model is fully open source under the Apache‑2.0 license.

Good at

  • Typed question answering
  • Single‑pass probability outputs
  • Low‑latency inference

Limits

  • No text generation
  • No vision support
  • Requires 8 k context for memory estimates

Best for

  • Rapid decision‑making in chatbots
  • Embedded inference on edge GPUs
  • Batch scoring of structured data

Who it’s for. Developers building decision‑oriented applications that need fast, deterministic probability outputs. Ideal for systems that integrate with Jev or System One APIs and require a lightweight, open‑source model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.8 GB 4.4 GB
Fits Get file →
Q5_K_M3.2 GB 4.8 GB
Fits Get file →
Q8_04.6 GB 6.2 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K_M quant (2.78 GB file, ~4.4 GB VRAM at 8 k context). If 12 GB VRAM is available, Q5_K_M (3.16 GB file, ~4.8 GB VRAM) offers higher precision. For maximum accuracy and 16 GB VRAM, Q8_0 (4.61 GB file, ~6.2 GB VRAM) is recommended. Memory estimates are approximate.

What GPU do you need for Jebadiah 4b 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: the best quant that fits is Q5_K_M (3.2 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.2 GB in use).

Which Jebadiah 4b v2 quant should you choose?

Q4_K_M is the usual starting point for Jebadiah 4b v2: it balances file size and quality well. Here it is a 2.8 GB file.

The Q8_0 file is 4.6 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

Architectureqwen35
Parameters4.33B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized byfrontier-infra
FamilyJebadiah
Licenseapache-2.0
Downloads (HF)2,486
Last updated2026-10-16

Frequently asked questions about Jebadiah 4b v2

How much VRAM does Jebadiah 4b v2 need?

About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 4b v2 on an 8 GB GPU?

Yes, with Q8_0: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Jebadiah 4b v2 GGUF?

It depends on the quant: Q4_K_M is 2.8 GB, Q5_K_M is 3.2 GB, Q8_0 is 4.6 GB.

What context length does Jebadiah 4b 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 4b v2 GGUF?

The files are on Hugging Face in the frontier-infra/jebadiah-4b-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 4b 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 4B v2 on 8 GB VRAM?

Yes, the Q4_K_M quant is 2.78 GB and requires about 4.4 GB VRAM at 8 k context, fitting within 8 GB.

Does this model support image inputs?

No, Jebadiah 4B v2 is a decision model and does not process vision data.

Is the model available for commercial use?

Yes, it is licensed under Apache‑2.0, allowing commercial deployment.

Other GGUFs of jebadiah-4b-v2

Similar models

Browse all →

More from frontier-infra

All by frontier-infra →

More Jebadiah models

All Jebadiah →

Other small models

All small models →