LL

Llama 3.3 70B Instruct Heretic

LlamaGGUF by mradermacherUpdated 2026-10-13
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Llama 3.3 70B Instruct Heretic needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 20 quants, from 26.4 GB (Q2_K) to 75.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Llama 3.3 70B Instruct Heretic – 70.6B parameter instruction‑tuned model

Llama 3.3 70B Instruct Heretic is a 70.6B parameter, instruction‑tuned language model. It supports multilingual dialogue in English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. The model is available in multiple GGUF quantizations for efficient inference.

Good at

  • Multilingual instruction following
  • Large context handling
  • High token throughput

Limits

  • Requires large VRAM for full precision
  • No vision or audio modalities
  • License is commercial

Best for

  • Chat assistants in multiple languages
  • Synthetic data generation
  • Model distillation pipelines

Who it’s for. Developers and researchers needing a high‑capacity multilingual instruction model for commercial or research applications. The model is suitable for building chatbots, content generation tools, and training data augmentation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS38.3 GB 41.5 GB
Too big Get file →
IQ4_XS38.3 GB 41.5 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q6_K57.9 GB 61.1 GB
Too big Get file →
Q8_075.0 GB 78.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (40.35 GB file, ~43.5 GB memory at 8k context). For 12 GB VRAM, Q5_K_S (48.66 GB file, ~51.8 GB memory). For 24 GB VRAM, Q6_K (57.89 GB file, ~61.1 GB memory). Estimates are approximate.

What GPU do you need for Llama 3.3 70B Instruct 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: 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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which Llama 3.3 70B Instruct Heretic quant should you choose?

Q4_K_M is the usual starting point for Llama 3.3 70B Instruct Heretic: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 GB, about 1.8 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 Q2_K at 26.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3.3
Downloads (HF)1,546
Last updated2026-10-13

Frequently asked questions about Llama 3.3 70B Instruct Heretic

How much VRAM does Llama 3.3 70B Instruct Heretic need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Llama 3.3 70B Instruct Heretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3.3 70B Instruct Heretic GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q2_K is 26.4 GB, Q3_K_S is 30.9 GB, Q3_K_S is 30.9 GB, Q3_K_M is 34.3 GB, Q3_K_M is 34.3 GB and 14 more.

What context length does Llama 3.3 70B Instruct Heretic support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Llama 3.3 70B Instruct Heretic GGUF?

The files are on Hugging Face in the mradermacher/Llama-3.3-70B-Instruct-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 Llama 3.3 70B Instruct Heretic use?

Hugging Face lists the license as llama3.3. 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 Llama 3.3 70B Instruct Heretic on 8 GB VRAM?

Use the Q4_K_S quantization; it requires about 43.5 GB memory at 8k context, so 8 GB VRAM is insufficient for full inference.

Does this model support vision or audio inputs?

No, the model is text‑only and does not include vision or audio modalities.

What license applies to this model?

The model is released under the Llama 3.3 Community License Agreement, a custom commercial license.

Other GGUFs of Llama-3.3-70B-Instruct-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →