LL

Nova 70B Llama 3.3

LlamaGGUF by LatitudeGamesUpdated 2025-09-01
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

Nova 70B Llama 3.3 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 24 quants, from 15.3 GB (IQ1_S) to 141.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Nova 70B Llama 3.3 – a large Llama model for roleplay and tool use

Nova 70B Llama 3.3 is a 70.6 billion‑parameter Llama model fine‑tuned for roleplay and tool use. It supports a 131072‑token context window and is available in multiple GGUF quantizations. The model is licensed under llama3.3.

Good at

  • Roleplay with consistent characters
  • Tool use in prompts
  • Long‑form narrative generation

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License is llama3.3

Best for

  • Interactive storytelling
  • Character‑driven games
  • Narrative writing

Who it’s for. Developers and content creators who need a large Llama model for roleplay or tool‑augmented tasks. The model is suitable for applications that can allocate sufficient VRAM and handle a 131072‑token context.

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_K_S24.5 GB 27.7 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 →
IQ4_NL40.1 GB 43.2 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 →
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 →
BF16141.1 GB (4 parts) 144.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (15.34 GB file, 18.5 GB memory). For 16 GB VRAM, IQ1_M (16.75 GB file, 19.9 GB memory). For 24 GB VRAM, Q2_K (26.38 GB file, 29.6 GB memory). Higher quants require proportionally more VRAM.

What GPU do you need for Nova 70B Llama 3.3?

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 Nova 70B Llama 3.3 quant should you choose?

Q4_K_M is the usual starting point for Nova 70B Llama 3.3: 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 context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byLatitudeGames
FamilyLlama
Licensellama3.3
Downloads (HF)590
Last updated2025-09-01

Frequently asked questions about Nova 70B Llama 3.3

How much VRAM does Nova 70B Llama 3.3 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 Nova 70B Llama 3.3 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 Nova 70B Llama 3.3 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 18 more.

What context length does Nova 70B Llama 3.3 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 Nova 70B Llama 3.3 GGUF?

The files are on Hugging Face in the LatitudeGames/Nova-70B-Llama-3.3-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 Nova 70B Llama 3.3 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 Nova 70B on 8 GB VRAM?

Use the IQ1_S quant, which requires about 18.5 GB of VRAM at 8k context. 8 GB VRAM is insufficient for this quant.

Does Nova support vision?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports up to 131072 tokens of context.

Other GGUFs of Nova-70B-Llama-3.3

Similar models

Browse all →

More from LatitudeGames

All by LatitudeGames →

More Llama models

All Llama →

Other large models

All large models →