GP

Gpt Oss 20b Heretic Ara v3

gpt-ossGGUF by mradermacherUpdated 2026-03-06
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant12.1 GB
Quick answer

Gpt Oss 20b Heretic Ara v3 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 12 quants, from 12.1 GB (Q3_K_S) to 22.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Gpt Oss 20b Heretic Ara v3 – 20.9B parameter GPT‑OSS model

Gpt Oss 20b Heretic Ara v3 is a 20.9B parameter GPT‑OSS model with a 131072 token context window. It is released under the Apache‑2.0 license and supports chain‑of‑thought reasoning, function calling, web browsing, Python execution and structured outputs. The model is available in multiple GGUF quantizations.

Good at

  • Large context reasoning
  • Agentic tasks like function calling
  • Chain‑of‑thought debugging

Limits

  • No vision support
  • Requires harmony response format
  • Large memory for higher quants

Best for

  • Local inference on 8‑16GB GPUs
  • Fine‑tuning for specialized tasks
  • Agentic applications with function calls

Who it’s for. Developers and researchers who need a large, open‑weight GPT‑OSS model for local deployment or fine‑tuning. The model is suitable for projects requiring advanced reasoning and agentic capabilities without commercial licensing constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S12.1 GB 13.0 GB
Too big Get file →
Q2_K12.1 GB 13.0 GB
Too big Get file →
MXFP4_MOE12.1 GB 13.0 GB
Too big Get file →
IQ4_XS12.2 GB 13.1 GB
Too big Get file →
Q3_K_M12.9 GB 13.8 GB
Too big Get file →
Q3_K_L13.3 GB 14.2 GB
Too big Get file →
Q4_K_S14.7 GB 15.6 GB
Too big Get file →
Q4_K_M15.8 GB 16.7 GB
Too big Get file →
Q5_K_S15.9 GB 16.8 GB
Too big Get file →
Q5_K_M16.9 GB 17.8 GB
Too big Get file →
Q6_K22.2 GB 23.1 GB
Too big Get file →
Q8_022.3 GB 23.2 GB
Too big Get file →

For 8GB VRAM, use Q3_K_S (12.06 GB file, ~13 GB memory at 8k context). For 16GB VRAM, Q4_K_S (14.65 GB file, ~15.6 GB memory) or Q4_K_M (15.81 GB file, ~16.7 GB memory). Higher quants like Q6_K or Q8_0 require >23 GB memory and are not suitable for 16GB GPUs.

What GPU do you need for Gpt Oss 20b Heretic Ara v3?

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 Q4_K_S (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).

Which Gpt Oss 20b Heretic Ara v3 quant should you choose?

Q4_K_M is the usual starting point for Gpt Oss 20b Heretic Ara v3: 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_S at 12.1 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 bymradermacher
Familygpt-oss
Licenseapache-2.0
Downloads (HF)4,179
Last updated2026-03-06

Frequently asked questions about Gpt Oss 20b Heretic Ara v3

How much VRAM does Gpt Oss 20b Heretic Ara v3 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 Heretic Ara v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gpt Oss 20b Heretic Ara v3 GGUF?

It depends on the quant: Q3_K_S is 12.1 GB, Q2_K is 12.1 GB, MXFP4_MOE is 12.1 GB, IQ4_XS is 12.2 GB, Q3_K_M is 12.9 GB, Q3_K_L is 13.3 GB and 6 more.

What context length does Gpt Oss 20b Heretic Ara v3 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 Heretic Ara v3 GGUF?

The files are on Hugging Face in the mradermacher/gpt-oss-20b-heretic-ara-v3-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 Heretic Ara v3 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 8GB VRAM?

Use the Q3_K_S quant, which has a 12.06 GB file size and requires about 13 GB memory at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities and is text‑only.

What license does the model use?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of gpt-oss-20b-heretic-ara-v3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →