Skip to content
Run LLM Locally

QwQ 32B on the RTX 3090 Ti

With 24 GB of VRAM, the RTX 3090 Ti runs QwQ 32B at Q4_K_M entirely on the GPU with an 8K context (about 22.4 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

QwQ 32B

Q4_K_M · 8K context

Compatible

The model needs about 22.4 GB and fits in the 23.3 GB available (0.9 GB left).

Your hardware
RTX 3090 Ti 24 GB · 64 GB RAM
Estimated memory
~22.4 GB estimate
VRAM (usable memory)
23.3 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
33–45 tok/s estimate
Largest context in fast memory
11K tokens
Confidence: low

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

Memory breakdown

~22.4 GB (21.6 GB–23.2 GB) needed · estimate

Fits entirely in VRAM · 0.9 GB left

  • Model weights18.5 GB
  • KV cache2 GB
  • Runtime overhead0.8 GB
  • Safety margin1.1 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

QwQ 32B on RTX 3090 Ti + 64 GB RAM · 8K context
QwQ 32B Q8_08K~37 GB · 1.4–2.5 tok/s estimatePossible but slow
QwQ 32B Q6_K8K~29.3 GB · 3–6 tok/s estimateCPU/GPU offload
QwQ 32B Q5_K_M8K~25.7 GB · 6.5–12 tok/s estimateCPU/GPU offload
QwQ 32B Q4_K_M8K~22.4 GB · 33–45 tok/s estimateCompatible
QwQ 32B IQ4_XS8K~20.3 GB · 36–50 tok/s estimateCompatible
QwQ 32B Q3_K_M8K~18.5 GB · 39–54 tok/s estimateExcellent

Alternatives

GPUs that run QwQ 32B 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

CompatibleRuns QwQ 32B 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 QwQ 32B?
The model needs about 22.4 GB and fits in the 23.3 GB available (0.9 GB left).
Which quantization should I use on the RTX 3090 Ti?
Q4_K_M is the highest-precision quantization that fits entirely in VRAM at 8K context. ~22.4 GB / 23.3 GB.
What is the largest context on the RTX 3090 Ti?
At Q4_K_M, about 11K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is QwQ 32B (RTX 3090 Ti)?
We estimate 33–45 tok/s (estimate, confidence low). Based on: memory bandwidth (1,008 GB/s) and model size.