JI

jiwo-0.8b

JiwoGGUF by breaksoftwareUpdated 2026-10-12
Download on Hugging Face
Parameters1.01B
Context256K
Layers24
Architectureqwen35
Smallest quant0.7 GB
Quick answer

jiwo-0.8b 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 3 quants, from 0.7 GB (Q4_K_M) to 2.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

jiwo-0.8b – a 1.01B parameter decision model

jiwo-0.8b is a decision model that reads a state and one or more typed questions and returns probabilities for each option in a single forward pass. It does not generate text. The model is built on the qwen35 architecture and is licensed under apache-2.0.

Good at

  • reasoning
  • tools
  • fast inference on GPUs

Limits

  • no vision support
  • trained context 262144 tokens
  • requires CUDA graphs for speed

Best for

  • decision making tasks
  • API integration via /v1/systemone
  • low‑latency inference

Who it’s for. Developers building decision‑making services that need quick, deterministic probability outputs. The model is suitable for integration into existing API pipelines that require a lightweight, non‑generative LLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.7 GB 1.6 GB
Fits Get file →
Q8_01.1 GB 2.0 GB
Fits Get file →
BF162.0 GB 2.9 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (0.67 GB file, ~1.6 GB memory at 8 k context). For 12 GB VRAM use Q8_0 (1.08 GB file, ~2 GB memory). For larger memory budgets use BF16 (2.03 GB file, ~2.9 GB memory).

What GPU do you need for jiwo-0.8b?

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 BF16 (2.0 GB file, about 2.9 GB in use).

Which jiwo-0.8b quant should you choose?

Q4_K_M is the usual starting point for jiwo-0.8b: 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

Architectureqwen35
Parameters1.01B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized bybreaksoftware
FamilyJiwo
Licenseapache-2.0
Downloads (HF)711
Last updated2026-10-12

Frequently asked questions about jiwo-0.8b

How much VRAM does jiwo-0.8b 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 jiwo-0.8b on an 8 GB GPU?

Yes, with BF16: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of jiwo-0.8b GGUF?

It depends on the quant: Q4_K_M is 0.7 GB, Q8_0 is 1.1 GB, BF16 is 2.0 GB.

What context length does jiwo-0.8b 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 jiwo-0.8b GGUF?

The files are on Hugging Face in the breaksoftware/jiwo-0.8b-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 jiwo-0.8b 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 jiwo-0.8b on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 1.6 GB of VRAM at 8 k context, which fits in 8 GB.

Does jiwo-0.8b support vision tasks?

No, the model does not have vision capabilities.

What is the maximum context length for jiwo-0.8b?

The model was trained with 262144 tokens and can handle that context length.

Similar models

Browse all →

More from breaksoftware

All by breaksoftware →

Other tiny models

All tiny models →