AR

ARIA 70B V2

AriaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant29.3 GB
Quick answer

ARIA 70B V2 needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.3 GB (Q2_K) to 48.8 GB (Q5_K_M).

ARIA 70B V2 – a 70‑billion‑parameter French‑focused Llama 2 fine‑tuned model

ARIA 70B V2 is a 70‑billion‑parameter Llama 2 model fine‑tuned on over 50,000 high‑quality French tokens. It supports 4,096‑token context by default and can be extended to >6,000 tokens with rope scaling. The model is available in GGUF format for llama.cpp and other GPU‑accelerated clients.

Good at

  • French language generation
  • Dialogue and chat scenarios
  • Coding assistance

Limits

  • Requires large VRAM for full precision
  • No vision or multimodal support
  • License governed by Meta’s Llama 2 terms

Best for

  • Developers building French chatbots
  • Researchers testing large‑language models
  • Users needing code generation in French

Who it’s for. The model is suited for developers and researchers who need a large, French‑optimized language model for text‑only tasks. It is ideal for local inference on systems with sufficient GPU memory and for integration into llama.cpp‑based pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K29.3 GB 31.1 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_M33.2 GB 35.0 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
Q4_038.9 GB 40.7 GB
Too big Get file →
Q4_K_S39.1 GB 40.9 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_047.5 GB 49.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 8 GB VRAM use Q4_K or Q4_K_S (≈42 GB memory at 8k context). For 12 GB VRAM Q5_K_S or Q5_K_M (≈51 GB). For 16 GB VRAM Q3_K_M or Q3_K_L (≈36–39 GB). Memory estimates are approximate.

What GPU do you need for ARIA 70B V2?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which ARIA 70B V2 quant should you choose?

Q4_K_M is the usual starting point for ARIA 70B V2: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 29.3 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byTheBloke
FamilyAria
Licensellama2
Downloads (HF)3,437
Last updated2023-09-27

Frequently asked questions about ARIA 70B V2

How much VRAM does ARIA 70B V2 need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 ARIA 70B V2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ARIA 70B V2 GGUF?

It depends on the quant: Q2_K is 29.3 GB, Q3_K_S is 29.9 GB, Q3_K_M is 33.2 GB, Q3_K_L is 36.1 GB, Q4_0 is 38.9 GB, Q4_K_S is 39.1 GB and 4 more.

What context length does ARIA 70B V2 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download ARIA 70B V2 GGUF?

The files are on Hugging Face in the TheBloke/ARIA-70B-V2-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 ARIA 70B V2 use?

Hugging Face lists the license as llama2. 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 ARIA 70B V2 on 8 GB VRAM?

Use the Q4_K or Q4_K_S quantised model; it requires about 42 GB of VRAM at 8k context, so 8 GB is insufficient.

Does ARIA 70B V2 support images?

No, the model is text‑only and does not include vision capabilities.

What license applies to ARIA 70B V2?

It is governed by the Meta Llama 2 license; users must accept the license before downloading.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Aria models

All Aria →

Other large models

All large models →