OL

Olmo 3 7B Think heretic

OLMoGGUF by richardyoungUpdated 2026-10-20
Download on Hugging Face
Parameters7.3B
Context64K
Layers32
Architectureolmo2
Smallest quant0.0 GB
Quick answer

Olmo 3 7B Think heretic needs about 9.3 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 0.0 GB to 7.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

Olmo 3 7B Think heretic – an abliterated 7B reasoning model

Olmo 3 7B Think heretic is a 7.3B parameter model from the OLMO family. It is an abliterated build that removes safety refusals while preserving reasoning ability. The model is open‑source under Apache‑2.0 and supports 65536 token context.

Good at

  • Reasoning tasks
  • Long‑form generation
  • Research use

Limits

  • No vision support
  • Large VRAM needed for higher quant
  • License requires compliance

Best for

  • Local inference on powerful GPUs
  • Educational alignment studies
  • Creative writing without safety filters

Who it’s for. Researchers, developers, and power users who need a large reasoning model that can be run locally without safety refusals. The model is suitable for experimentation and unrestricted inference, but should be used responsibly.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 4.8 GB
Fits Get file →
IQ3_M3.5 GB 8.3 GB
Too big Get file →
IQ4_XS4.0 GB 8.8 GB
Too big Get file →
Q4_K_M4.5 GB 9.3 GB
Too big Get file →
Q5_K_M5.2 GB 10.0 GB
Too big Get file →
Q6_K6.0 GB 10.8 GB
Too big Get file →
Q8_07.8 GB 12.6 GB
Too big Get file →

For 8 GB VRAM, use IQ3_M (8.3 GB memory) or IQ4_XS (8.8 GB). For 12 GB VRAM, Q4_K_M (9.3 GB) or Q5_K_M (10 GB) are suitable. Higher quants like Q6_K or Q8_0 require 10.8 GB and 12.6 GB respectively and are best on 16 GB+ GPUs.

What GPU do you need for Olmo 3 7B Think heretic?

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 the main file (0.0 GB file, about 4.8 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 10.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.8 GB file, about 12.6 GB in use).

Which Olmo 3 7B Think heretic quant should you choose?

Q4_K_M is the usual starting point for Olmo 3 7B Think heretic: it balances file size and quality well. Here it is a 4.5 GB file.

The Q8_0 file is 7.8 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.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureolmo2
Parameters7.3B
Layers32
Trained context65,536 tokens
KV cache (fp16)512 KB per token

Source

Quantized byrichardyoung
FamilyOLMo
Licenseapache-2.0
Downloads (HF)832
Last updated2026-10-20

Frequently asked questions about Olmo 3 7B Think heretic

How much VRAM does Olmo 3 7B Think heretic need?

About 9.3 GB at Q4_K_M with an 8K context window. That is the 4.5 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 Olmo 3 7B Think heretic on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Olmo 3 7B Think heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ3_M is 3.5 GB, IQ4_XS is 4.0 GB, Q4_K_M is 4.5 GB, Q5_K_M is 5.2 GB, Q6_K is 6.0 GB and 1 more.

What context length does Olmo 3 7B Think heretic support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download Olmo 3 7B Think heretic GGUF?

The files are on Hugging Face in the richardyoung/Olmo-3-7B-Think-heretic-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 Olmo 3 7B Think heretic 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 Olmo 3 7B Think heretic on 8 GB VRAM?

Yes, the IQ3_M quant uses about 8.3 GB memory at 8 k context, which fits on 8 GB VRAM with some headroom.

Does this model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is released under the Apache‑2.0 license.

Other GGUFs of Olmo-3-7B-Think-heretic

Similar models

Browse all →

More from richardyoung

All by richardyoung →

More OLMo models

All OLMo →

Other small models

All small models →