GP

gpt oss 20b hermes agent tool finetune

gpt-ossGGUF by fesalfayedUpdated 2026-05-02
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant12.9 GB
Quick answer

gpt oss 20b hermes agent tool finetune needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 12.9 GB (Q3_K_M) to 41.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

gpt-oss-20b Hermes-Agent tool finetune for reliable function calling

A 20.9‑billion‑parameter Mixture‑of‑Experts model fine‑tuned for tool use. It retains the Harmony chat template and reasoning‑effort knob, and improves function‑calling adherence and multi‑turn agent loops.

Good at

  • Reliable function calling
  • Long multi‑turn agent loops
  • System‑prompt fidelity

Limits

  • Requires 131072 context tokens
  • No vision support
  • Apache‑2.0 license restricts commercial use only with license compliance

Best for

  • Local agent frameworks
  • Tool‑centric workflows
  • Multi‑step instruction following

Who it’s for. Developers building local agents that need consistent tool usage and multi‑turn reasoning. The model is suitable for projects that require a fine‑tuned, open‑weight GPT‑style model with a permissive license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M12.9 GB 13.8 GB
Too big Get file →
Q4_K_M15.8 GB 16.7 GB
Too big Get file →
Q5_K_M16.9 GB 17.8 GB
Too big Get file →
Q8_022.3 GB 23.2 GB
Too big Get file →
F1641.9 GB 42.8 GB
Too big Get file →

For 16 GB RAM, use Q4_K_M (file size 15.81 GB, estimated 16.7 GB memory at 8 k context). For higher quality with more memory, use Q8_0 (22.26 GB, 23.2 GB memory). Smaller quants like Q3_K_M (12.92 GB, 13.8 GB memory) fit tighter budgets.

What GPU do you need for gpt oss 20b hermes agent tool finetune?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_M (12.9 GB file, about 13.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (41.9 GB file, about 42.8 GB in use).

Which gpt oss 20b hermes agent tool finetune quant should you choose?

Q4_K_M is the usual starting point for gpt oss 20b hermes agent tool finetune: it balances file size and quality well. Here it is a 15.8 GB file.

The Q8_0 file is 22.3 GB, about 1.4 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.

If memory is tight, the smallest file is Q3_K_M at 12.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized byfesalfayed
Familygpt-oss
Licenseapache-2.0
Downloads (HF)1,484
Last updated2026-05-02

Frequently asked questions about gpt oss 20b hermes agent tool finetune

How much VRAM does gpt oss 20b hermes agent tool finetune need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 gpt oss 20b hermes agent tool finetune on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gpt oss 20b hermes agent tool finetune GGUF?

It depends on the quant: Q3_K_M is 12.9 GB, Q4_K_M is 15.8 GB, Q5_K_M is 16.9 GB, Q8_0 is 22.3 GB, F16 is 41.9 GB.

What context length does gpt oss 20b hermes agent tool finetune support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 gpt oss 20b hermes agent tool finetune GGUF?

The files are on Hugging Face in the fesalfayed/gpt-oss-20b-hermes_agent-tool-finetune_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 gpt oss 20b hermes agent tool finetune 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?

No, the smallest quant requires at least 13.8 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

No, the model has no vision capability.

What license applies to this model?

The model is released under Apache‑2.0, allowing free use with no copyleft restrictions.

Other GGUFs of gpt-oss-20b

Similar models

Browse all →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →