LL

Llama 3.3 70B Instruct Abliterated

LlamaGGUF by mradermacherUpdated 2024-12-13
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Llama 3.3 70B Instruct Abliterated 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 9 quants, from 26.4 GB (Q2_K) to 49.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Llama 3.3 70B Instruct Abliterated – a large instruction‑tuned model with refusal removal.

Llama 3.3 70B Instruct Abliterated is a 70‑billion‑parameter instruction model that has been modified to reduce refusal behavior. It supports a 131,072‑token context window and is available in several GGUF quantizations. The model is released under the llama3.3 license.

Good at

  • Large context handling
  • Instruction following
  • Reduced refusal responses

Limits

  • No vision support
  • Requires high VRAM for full precision
  • License restricts commercial use

Best for

  • Long‑form content generation
  • Complex instruction chains
  • Research prototyping

Who it’s for. Developers and researchers who need a large instruction model with lower refusal rates. The model is suitable for local deployment via llama.cpp or transformers, but requires sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
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_M34.3 GB 37.5 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 →
Q4_K_S40.3 GB 43.5 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_M49.9 GB 53.1 GB
Too big Get file →

For 8 GB VRAM use Q2_K (26.38 GB file, ~29.6 GB VRAM). For 12 GB VRAM use Q3_K_S (30.91 GB file, ~34.1 GB VRAM). For 16 GB VRAM use Q4_K_S (40.35 GB file, ~43.5 GB VRAM). Estimates are approximate.

What GPU do you need for Llama 3.3 70B Instruct Abliterated?

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 Abliterated quant should you choose?

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

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)38,541
Last updated2024-12-13

Frequently asked questions about Llama 3.3 70B Instruct Abliterated

How much VRAM does Llama 3.3 70B Instruct Abliterated 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 Abliterated 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 Abliterated GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q3_K_S is 30.9 GB, Q3_K_M is 34.3 GB, Q3_K_L is 37.1 GB, IQ4_XS is 38.3 GB, Q4_K_S is 40.3 GB and 3 more.

What context length does Llama 3.3 70B Instruct Abliterated 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 Abliterated GGUF?

The files are on Hugging Face in the mradermacher/Llama-3.3-70B-Instruct-abliterated-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 Abliterated 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 Abliterated on 8 GB VRAM?

Use the Q2_K quantization; it requires about 29.6 GB VRAM at 8 k context, so 8 GB is insufficient. A smaller model or higher VRAM is needed.

Does this model support image inputs?

No, the model has no vision capability.

What license applies to this model?

The model is released under the llama3.3 license, which may restrict commercial use.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →