Can RTX 4090 run Euryale L3.3 70B v2.3?

Yes — runs locally

~0 tok/sec · Cannot run — insufficient VRAM

Your VRAM

24 GB

Model size

70B

Best quant

Q4_K_M

VRAM needed

40.1 GB

The verdict

The RTX 4090 (24 GB VRAM) handles Euryale L3.3 70B v2.3 comfortably using the Q4_K_M quantization, which fits in 40.1 GB. Expected throughput is around 0 tokens/second, which feels Cannot run — insufficient VRAM in interactive use. Canonical 70B creative-writing and roleplay model. Llama-3.3-70B base with extended training on long-form prose. The reference 70B uncensored pick.

How to run it

1. Install Ollama or LM Studio.
2. Pull the Q4_K_M GGUF — best balance of quality and speed on 24 GB.
3. Start chatting. Expect ~0 tok/sec on first-token, faster after warmup.

See full Euryale L3.3 70B v2.3 setup →

Other models that run great on RTX 4090

FAQ (20)

What GPU do I need to run Euryale L3.3 70B v2.3?

To run Euryale L3.3 70B v2.3, you need a GPU with at least 40.1 GB of VRAM, but up to 140.5 GB depending on the quantization level.

Is Euryale L3.3 70B v2.3 good for coding?

Euryale L3.3 70B v2.3 is primarily designed for creative writing and roleplay, so its performance in coding tasks may not be as strong as specialized coding models.

Euryale L3.3 70B v2.3 vs Llama 3.1 8B?

Euryale L3.3 70B v2.3 has 70 billion parameters and is optimized for creative writing, while Llama 3.1 8B has 8 billion parameters and may be more suitable for general tasks or environments with limited resources.

Can I run Euryale L3.3 70B v2.3 on a Mac?

Yes, you can run Euryale L3.3 70B v2.3 on a Mac, but you will need a Mac with a compatible GPU and sufficient VRAM to handle the model's size.

How much VRAM does Euryale L3.3 70B v2.3 need?

Euryale L3.3 70B v2.3 requires between 40.1 GB and 140.5 GB of VRAM, depending on the quantization level used.

Is Euryale L3.3 70B v2.3 censored?

No, Euryale L3.3 70B v2.3 is an uncensored model, making it suitable for creative writing and roleplay without content restrictions.

Is Euryale L3.3 70B v2.3 commercial-use allowed?

Euryale L3.3 70B v2.3 is licensed under the Llama-3 license, which typically allows commercial use, but you should review the specific terms for any restrictions.

Euryale L3.3 70B v2.3 context length?

Euryale L3.3 70B v2.3 has a context length of 131,072 tokens, allowing it to process very long sequences of text.

Want personalized recommendations for your exact setup? Detect my hardware →