LL

PatronusAI Llama 3 Patronus Lynx 70B Instruct

LlamaGGUF by RichardErkhovUpdated 2024-09-08
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

PatronusAI Llama 3 Patronus Lynx 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 22 quants, from 26.4 GB (Q2_K) to 75.0 GB (Q8_0).

PatronusAI Llama 3 Patronus Lynx 70B Instruct – hallucination detection model

Patronus Lynx 70B Instruct is a fine‑tuned Llama‑3 model for detecting hallucinations in RAG settings. It evaluates a document, question and answer pair and outputs "PASS" or "FAIL". The model supports up to 8192 context tokens.

Good at

  • Hallucination detection
  • RAG evaluation
  • Faithfulness scoring

Limits

  • Requires 70.6B parameters
  • No vision support
  • CC‑BY‑NC‑4.0 license

Best for

  • RAG pipelines
  • Content verification
  • QA quality control

Who it’s for. Developers building retrieval‑augmented generation systems that need a reliable hallucination checker. Researchers evaluating faithfulness in language models.

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_K34.3 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 →
IQ4_XS38.3 GB 41.5 GB
Too big Get file →
Q4_040.0 GB 43.2 GB
Too big Get file →
IQ4_NL40.3 GB (2 parts) 43.5 GB
Too big Get file →
Q4_K_S40.3 GB (2 parts) 43.5 GB
Too big Get file →
Q4_K42.5 GB (2 parts) 45.7 GB
Too big Get file →
Q4_K_M42.5 GB (2 parts) 45.7 GB
Too big Get file →
Q4_144.3 GB (2 parts) 47.5 GB
Too big Get file →
Q5_048.7 GB (2 parts) 51.8 GB
Too big Get file →
Q5_K_S48.7 GB (2 parts) 51.8 GB
Too big Get file →
Q5_K49.9 GB (2 parts) 53.1 GB
Too big Get file →
Q5_K_M49.9 GB (2 parts) 53.1 GB
Too big Get file →
Q5_153.0 GB (2 parts) 56.2 GB
Too big Get file →
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →

For 8‑GB VRAM use Q2_K (26.38 GB file, ~29.6 GB memory). For 12‑GB VRAM use Q3_K_S (30.91 GB file, ~34.1 GB memory). For 24‑GB VRAM use Q4_K_M (42.52 GB file, ~45.7 GB memory).

What GPU do you need for PatronusAI Llama 3 Patronus Lynx 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: 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_1 (44.3 GB file, about 47.5 GB in use).

Which PatronusAI Llama 3 Patronus Lynx 70B Instruct quant should you choose?

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

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)1,056
Last updated2024-09-08

Frequently asked questions about PatronusAI Llama 3 Patronus Lynx 70B Instruct

How much VRAM does PatronusAI Llama 3 Patronus Lynx 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 PatronusAI Llama 3 Patronus Lynx 70B Instruct 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 PatronusAI Llama 3 Patronus Lynx 70B Instruct 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 is 34.3 GB and 16 more.

What context length does PatronusAI Llama 3 Patronus Lynx 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 PatronusAI Llama 3 Patronus Lynx 70B Instruct GGUF?

The files are on Hugging Face in the RichardErkhov/PatronusAI_-_Llama-3-Patronus-Lynx-70B-Instruct-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 PatronusAI Llama 3 Patronus Lynx 70B Instruct use?

Hugging Face lists the license as cc-by-nc-4.0. 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 this model on 8 GB VRAM?

Yes, the Q2_K quantization requires about 29.6 GB memory at 8k context, which can be managed on 8 GB VRAM with off‑load or batching.

Does the model support image inputs?

No, the model is text‑only and has no vision capabilities.

What license applies to this model?

The model is licensed under CC‑BY‑NC‑4.0, allowing non‑commercial use with attribution.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other large models

All large models →