OP

opendecider small td

OpendeciderGGUF by manjunathshivaUpdated 2026-10-10
Download on Hugging Face
Parameters4.02B
Context256K
Layers36
Architectureqwen3
Smallest quant2.5 GB
Quick answer

opendecider small td needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.5 GB (Q4_K_M) to 4.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

OpenDecider-small-td: 4B decision model fine‑tuned for business workflows

OpenDecider-small-td is a 4.02B parameter Qwen3 model fine‑tuned for typed‑decision tasks such as customer service, invoice processing, security incidents and agent‑trace monitoring. It is released under Apache‑2.0 and supports tools.

Good at

  • Business workflow decisions
  • Typed‑decision answering
  • Probability‑based option selection

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No mixture of experts

Best for

  • Ticket triage
  • Invoice checks
  • Security alert triage

Who it’s for. Developers building business automation tools that need reliable decision probabilities. The model is suitable for integration into LM Studio, Ollama, or vLLM pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.5 GB, estimated 4.2 GB memory at 8k context). For 16 GB VRAM, Q8_0 (file size 4.28 GB, estimated 6 GB memory at 8k context) provides full precision. Both are available from the GGUF repo.

What GPU do you need for opendecider small td?

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 Q8_0 (4.3 GB file, about 6.0 GB in use).

Which opendecider small td quant should you choose?

Q4_K_M is the usual starting point for opendecider small td: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 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

Architectureqwen3
Parameters4.02B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymanjunathshiva
Licenseapache-2.0
Downloads (HF)351
Last updated2026-10-10

Frequently asked questions about opendecider small td

How much VRAM does opendecider small td need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 opendecider small td on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of opendecider small td GGUF?

It depends on the quant: Q4_K_M is 2.5 GB, Q8_0 is 4.3 GB.

What context length does opendecider small td support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download opendecider small td GGUF?

The files are on Hugging Face in the manjunathshiva/opendecider-small-td-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 opendecider small td 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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantized build uses about 4.2 GB of VRAM at 8k context, fitting within an 8 GB GPU.

Does the model support image inputs?

No, the model has no vision capabilities and only processes text or JSON.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from manjunathshiva

All by manjunathshiva →

More Opendecider models

All Opendecider →

Other small models

All small models →