How much VRAM does the NVIDIA RTX 4090 have?

The NVIDIA RTX 4090 has 24 GB of GDDR6X with 1008 GB/s memory bandwidth.

What is the NVIDIA RTX 4090 best for?

With 24 GB of VRAM, the NVIDIA RTX 4090 is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.

What LLMs can the NVIDIA RTX 4090 run locally?

The NVIDIA RTX 4090 can run 42 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at BF16, Llama 3.2 3B Instruct at FP32, Llama 3.2 1B Instruct at FP32.

Can the NVIDIA RTX 4090 run Llama 3.3 70B Instruct?

The NVIDIA RTX 4090 can run Llama 3.3 70B Instruct with CPU offload at NVFP4 quantization, but inference will be slower than native VRAM execution.

Can the NVIDIA RTX 4090 run Qwen 3.6 27B?

Yes. The NVIDIA RTX 4090 runs Qwen 3.6 27B natively in VRAM at NVFP4 quantization, achieving approximately 74.7 tokens per second.

Can the NVIDIA RTX 4090 run Llama 3.1 8B Instruct?

Yes. The NVIDIA RTX 4090 runs Llama 3.1 8B Instruct natively in VRAM at BF16 quantization, achieving approximately 63 tokens per second.

NVIDIA RTX 4090

The NVIDIA RTX 4090 has 24 GB VRAM and 1008 GB/s memory bandwidth. It can run 42 of our 70 tracked models natively in VRAM at 8k context.

With 24 GB GDDR6X, the NVIDIA RTX 4090 is a consumer-tier GPU that can run 42 models natively. It handles 70B-class models at Q4 quantization.

NVIDIA RTX 4090: October 2022 flagship with 24GB GDDR6X at 1008 GB/s. The community standard for high-end local LLM.

Runs 7B-32B models at Q4 natively with room for context. 70B models need CPU offload or dual-GPU. ~12-20 t/s for 7B Q4, ~6-10 t/s for 32B Q4.

Best consumer CUDA support. llama.cpp, Ollama, vLLM, TensorRT-LLM all optimized. EXL2 and GGUF quantizations widely available.

Vendor	NVIDIA
Architecture	Ada Lovelace
VRAM	24 GB
Memory type	GDDR6X
Memory bandwidth	1008 GB/s
Compute backend	CUDA
Tier	Consumer
Released	2022
Models (native)	42 / 70
Models (offload)	11 / 70

Software: Full llama.cpp and Ollama support out of the box. CUDA 12.x recommended; driver ≥ 525 required.

Popular models for this GPU

Mixtral 8x7B Instruct v0.1 Qwen 3.5 35B-A3B (MoE)Qwen 3.6 35B Yi 1.5 34B Chat Qwen3 32B

Models this GPU runs natively in VRAM (42)

Models that fit with CPU offload (11)

These use system RAM for layers that don't fit in VRAM — expect much slower inference.

Too large for this GPU (17)

Compare NVIDIA RTX 4090 with other GPUs

Frequently asked questions

How much VRAM does the NVIDIA RTX 4090 have?: The NVIDIA RTX 4090 has 24 GB of GDDR6X with 1008 GB/s memory bandwidth.
What is the NVIDIA RTX 4090 best for?: With 24 GB of VRAM, the NVIDIA RTX 4090 is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.
What LLMs can the NVIDIA RTX 4090 run locally?: The NVIDIA RTX 4090 can run 42 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at BF16, Llama 3.2 3B Instruct at FP32, Llama 3.2 1B Instruct at FP32.
Can the NVIDIA RTX 4090 run Llama 3.3 70B Instruct?: The NVIDIA RTX 4090 can run Llama 3.3 70B Instruct with CPU offload at NVFP4 quantization, but inference will be slower than native VRAM execution.
Can the NVIDIA RTX 4090 run Qwen 3.6 27B?: Yes. The NVIDIA RTX 4090 runs Qwen 3.6 27B natively in VRAM at NVFP4 quantization, achieving approximately 74.7 tokens per second.
Can the NVIDIA RTX 4090 run Llama 3.1 8B Instruct?: Yes. The NVIDIA RTX 4090 runs Llama 3.1 8B Instruct natively in VRAM at BF16 quantization, achieving approximately 63 tokens per second.