LL

calme 2.2 llama3 70b

LlamaGGUF by MaziyarPanahiUpdated 2024-07-20
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

calme 2.2 llama3 70b 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 14 quants, from 15.3 GB (IQ1_S) to 141.1 GB.

Calme 2.2 Llama3 70B fine‑tuned for instruction following

Calme 2.2 is a DPO fine‑tuned version of Meta‑Llama‑3‑70B‑Instruct. It supports a 8192 token context window and uses the ChatML prompt template. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Long‑form dialogue
  • Contextual reasoning

Limits

  • No vision support
  • License not specified
  • Requires large VRAM for full precision

Best for

  • Chatbot development
  • Research prototyping
  • Content generation

Who it’s for. Developers and researchers needing a large instruction‑tuned Llama3 model for local deployment. Suitable for applications that can accommodate the model’s memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.3 GB (6 parts) 18.5 GB
Too big Get file →
IQ1_M16.8 GB (6 parts) 19.9 GB
Too big Get file →
Q2_K26.4 GB (6 parts) 29.6 GB
Too big Get file →
Q3_K_S30.9 GB (6 parts) 34.1 GB
Too big Get file →
Q3_K_M34.3 GB (6 parts) 37.5 GB
Too big Get file →
Q3_K_L37.1 GB (6 parts) 40.3 GB
Too big Get file →
IQ4_XS37.9 GB (6 parts) 41.1 GB
Too big Get file →
Q4_K_S40.3 GB (6 parts) 43.5 GB
Too big Get file →
Q4_K_M42.5 GB (6 parts) 45.7 GB
Too big Get file →
Q5_K_S48.7 GB (6 parts) 51.8 GB
Too big Get file →
Q5_K_M49.9 GB (6 parts) 53.1 GB
Too big Get file →
Q6_K57.9 GB (6 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (6 parts) 78.2 GB
Too big Get file →
—141.1 GB (6 parts) 144.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (15.34 GB file, ~18.5 GB VRAM). For 16 GB VRAM, Q4_K_S (40.35 GB file, ~43.5 GB VRAM) or Q4_K_M (42.52 GB file, ~45.7 GB VRAM). For 24 GB VRAM, Q5_K_S (48.66 GB file, ~51.8 GB VRAM) is recommended. Memory estimates are approximate.

What GPU do you need for calme 2.2 llama3 70b?

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 IQ1_M (16.8 GB file, about 19.9 GB in use).
  • 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 calme 2.2 llama3 70b quant should you choose?

Q4_K_M is the usual starting point for calme 2.2 llama3 70b: 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 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 byMaziyarPanahi
FamilyLlama
Downloads (HF)4,423
Last updated2024-07-20

Frequently asked questions about calme 2.2 llama3 70b

How much VRAM does calme 2.2 llama3 70b 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 calme 2.2 llama3 70b 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 calme 2.2 llama3 70b GGUF?

It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, 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 and 8 more.

What context length does calme 2.2 llama3 70b 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 calme 2.2 llama3 70b GGUF?

The files are on Hugging Face in the MaziyarPanahi/calme-2.2-llama3-70b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Calme 2.2 on 8 GB VRAM?

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

Does this model support vision tasks?

No, the model has no vision capabilities.

What prompt format does it use?

It uses the ChatML prompt template.

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Llama models

All Llama →

Other large models

All large models →