LL

Llama-3-70B-Instruct-norefusal

LlamaGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Llama-3-70B-Instruct-norefusal 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 12 quants, from 26.4 GB (Q2_K) to 49.9 GB (Q5_K_M).

Llama‑3‑70B‑Instruct‑norefusal – 70.6B parameter instruction model

Llama‑3‑70B‑Instruct‑norefusal is a 70.6B parameter model from the Llama family. It supports a 8192 token context window and is available in multiple GGUF quantizations. The model is released under the llama3 license.

Good at

  • Large‑scale instruction following
  • High‑capacity text generation
  • Long‑context handling

Limits

  • No vision support
  • No refusal logic fully tested
  • Requires large VRAM for higher quants

Best for

  • Enterprise chatbots
  • Research prototyping
  • Content creation at scale

Who it’s for. Developers and researchers needing a large instruction‑tuned model for text‑only workloads. The model is suitable for environments with sufficient GPU memory to run the desired quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 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, Q3_K_S (30.91 GB file, ~34.1 GB VRAM). For 24 GB VRAM, Q4_K_M (42.52 GB file, ~45.7 GB VRAM). Estimates are approximate.

What GPU do you need for Llama-3-70B-Instruct-norefusal?

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-3-70B-Instruct-norefusal quant should you choose?

Q4_K_M is the usual starting point for Llama-3-70B-Instruct-norefusal: 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 context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensellama3
Downloads (HF)758
Last updated2024-05-06

Frequently asked questions about Llama-3-70B-Instruct-norefusal

How much VRAM does Llama-3-70B-Instruct-norefusal 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-3-70B-Instruct-norefusal 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-3-70B-Instruct-norefusal GGUF?

It depends on the quant: Q2_K is 26.4 GB, IQ3_XS is 29.3 GB, IQ3_S is 30.9 GB, Q3_K_S is 30.9 GB, IQ3_M is 31.9 GB, Q3_K_M is 34.3 GB and 6 more.

What context length does Llama-3-70B-Instruct-norefusal support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Llama-3-70B-Instruct-norefusal GGUF?

The files are on Hugging Face in the mradermacher/Llama-3-70B-Instruct-norefusal-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-3-70B-Instruct-norefusal use?

Hugging Face lists the license as llama3. 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?

Use the Q2_K quant, which requires about 29.6 GB VRAM at 8k context. 8 GB VRAM is insufficient.

Does this model refuse instructions?

The model may still refuse some instructions; it is not fully tested for refusal behavior.

What license applies to this model?

The model is released under the llama3 license.

Other GGUFs of Llama-3-70B-Instruct-norefusal

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →