Skip to content
Run LLM Locally

Qwen3 8B on the RTX 3090 Ti

With 24 GB of VRAM, the RTX 3090 Ti runs Qwen3 8B at Q4_K_M entirely on the GPU with an 8K context (about 6.9 GB needed). At Q8_0 it fits entirely.

ShareFacebookXWhatsAppLinkedInEmail

Qwen3 8B

Q4_K_M · 8K context

Excellent

The model needs about 6.9 GB and fits in the 23.3 GB available, with 16.3 GB to spare.

Your hardware
RTX 3090 Ti 24 GB · 64 GB RAM
Estimated memory
~6.9 GB estimate
VRAM (usable memory)
23.3 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
107–157 tok/s estimate
Largest context in fast memory
118K tokens
Confidence: low

Based on: memory bandwidth (1,008 GB/s) and model size

Memory breakdown

~6.9 GB (6.5 GB–7.4 GB) needed · estimate

Fits entirely in VRAM · 16.3 GB left

  • Model weights4.7 GB
  • KV cache1.1 GB
  • Runtime overhead0.8 GB
  • Safety margin0.3 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (CUDA) · flash attention on · weights = real file size

EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • no benchmark for this hardware and model yet

Other quantizations on the RTX 3090 Ti

Qwen3 8B on RTX 3090 Ti + 64 GB RAM · 8K context
Qwen3 8B Q8_08K~10.5 GB · 71–99 tok/s estimateExcellent
Qwen3 8B Q6_K8K~8.6 GB · 86–124 tok/s estimateExcellent
Qwen3 8B Q5_K_M8K~7.7 GB · 96–139 tok/s estimateExcellent
Qwen3 8B Q4_K_M8K~6.9 GB · 107–157 tok/s estimateExcellent
Qwen3 8B IQ4_XS8K~6.5 GB · 114–169 tok/s estimateExcellent
Qwen3 8B Q3_K_M8K~6.1 GB · 122–183 tok/s estimateExcellent

Alternatives

GPUs that run Qwen3 8B Q4_K_M entirely in VRAM

Other models that fit the RTX 3090 Ti

Where to buy a RTX 3090 Ti

Prices and links follow the market you choose.

GeForce RTX 3090 Ti

24 GB GDDR6X · 1,008 GB/s · 450 W

ExcellentRuns Qwen3 8B Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the RTX 3090 Ti run Qwen3 8B?
The model needs about 6.9 GB and fits in the 23.3 GB available, with 16.3 GB to spare.
Which quantization should I use on the RTX 3090 Ti?
Q8_0 is the highest-precision quantization that fits entirely in VRAM at 8K context. ~10.5 GB / 23.3 GB.
What is the largest context on the RTX 3090 Ti?
At Q4_K_M, about 118K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Qwen3 8B (RTX 3090 Ti)?
We estimate 107–157 tok/s (estimate, confidence low). Based on: memory bandwidth (1,008 GB/s) and model size.