LL

Cat-Llama-3-70B-instruct

LlamaGGUF by mradermacherUpdated 2024-05-07
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

Cat-Llama-3-70B-instruct 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 15.3 GB (IQ1_S) to 49.9 GB (Q5_K_M).

Cat‑Llama‑3‑70B‑instruct – a 70B llama3 model fine‑tuned for system prompt fidelity and character immersion

Cat‑Llama‑3‑70B‑instruct is a 70.6B parameter llama3 model trained on GPT‑4 quality instruction data. It emphasizes system instruction fidelity, chain of thought, and character immersion. The model is available in multiple GGUF quantizations.

Good at

  • System prompt fidelity
  • Chain of thought reasoning
  • Character role play

Limits

  • No vision support
  • Requires 8k context
  • License is llama3

Best for

  • Chatbot with strict system prompts
  • Role‑play simulations
  • Scientific Q&A

Who it’s for. Developers and researchers who need a large llama3 model that respects system instructions and supports detailed chain‑of‑thought reasoning. The model is suitable for applications requiring high fidelity to prompts and immersive character interactions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.3 GB 18.5 GB
Too big Get file →
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_S22.2 GB 25.4 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 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_XS37.9 GB 41.1 GB
Too big Get file →
Q4_040.1 GB 43.3 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 IQ1_S (file size 15.34 GB, estimated 18.5 GB memory). For 12‑GB VRAM, IQ1_M (16.75 GB, 19.9 GB). For 24‑GB VRAM, Q4_K_M (42.52 GB, 45.7 GB) or Q5_K_M (49.95 GB, 53.1 GB).

What GPU do you need for Cat-Llama-3-70B-instruct?

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: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 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 Cat-Llama-3-70B-instruct quant should you choose?

Q4_K_M is the usual starting point for Cat-Llama-3-70B-instruct: it balances file size and quality well. Here it is a 42.5 GB file.

If memory is tight, the smallest file is IQ1_S at 15.3 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)669
Last updated2024-05-07

Frequently asked questions about Cat-Llama-3-70B-instruct

How much VRAM does Cat-Llama-3-70B-instruct 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 Cat-Llama-3-70B-instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Cat-Llama-3-70B-instruct GGUF?

It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, IQ2_M is 24.1 GB and 14 more.

What context length does Cat-Llama-3-70B-instruct 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 Cat-Llama-3-70B-instruct GGUF?

The files are on Hugging Face in the mradermacher/Cat-Llama-3-70B-instruct-i1-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 Cat-Llama-3-70B-instruct 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 Cat‑Llama‑3‑70B‑instruct on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 18.5 GB of VRAM at 8k context, so 8 GB is insufficient.

Does the model support vision tasks?

No, the model has no vision capabilities.

What context length does the model support?

The model was trained on 8192 tokens and supports up to 8192 tokens of context.

Other GGUFs of Cat-Llama-3-70B-instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →