Skip to content
Run LLM Locally

Qwen3.5 9B on the RTX 3080

With 10 GB of VRAM, the RTX 3080 runs Qwen3.5 9B at Q4_K_M entirely on the GPU with an 8K context (about 6.9 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Qwen3.5 9B

Q4_K_M · 8K context

Excellent

The model needs about 6.9 GB and fits in the 9.7 GB available, with 2.7 GB to spare.

Your hardware
RTX 3080 10 GB · 64 GB RAM
Estimated memory
~6.9 GB estimate
VRAM (usable memory)
9.7 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
84–119 tok/s estimate
Largest context in fast memory
91K tokens
Confidence: low

Based on: memory bandwidth (760 GB/s) and model size

Memory breakdown

~6.9 GB (6.4 GB–7.4 GB) needed · estimate

Fits entirely in VRAM · 2.7 GB left

  • Model weights5.3 GB
  • KV cache0.3 GB
  • Runtime overhead1 GB
  • Safety margin0.3 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (CUDA) · flash attention on · weights = real file size

EstimateData updated 40 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 3080

Qwen3.5 9B on RTX 3080 + 64 GB RAM · 8K context
Qwen3.5 9B Q8_08K~10.7 GB · 15–28 tok/s estimateCPU/GPU offload
Qwen3.5 9B Q6_K8K~8.6 GB · 67–93 tok/s estimateCompatible
Qwen3.5 9B Q5_K_M8K~7.8 GB · 75–104 tok/s estimateExcellent
Qwen3.5 9B Q4_K_M8K~6.9 GB · 84–119 tok/s estimateExcellent
Qwen3.5 9B IQ4_XS8K~6.4 GB · 91–129 tok/s estimateExcellent
Qwen3.5 9B Q3_K_M8K~5.9 GB · 99–141 tok/s estimateExcellent

Alternatives

GPUs that run Qwen3.5 9B Q4_K_M entirely in VRAM

Other models that fit the RTX 3080

Where to buy a RTX 3080

Prices and links follow the market you choose.

GeForce RTX 3080 (10 GB)

10 GB GDDR6X · 760 GB/s · 320 W

ExcellentRuns Qwen3.5 9B 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 3080 run Qwen3.5 9B?
The model needs about 6.9 GB and fits in the 9.7 GB available, with 2.7 GB to spare.
Which quantization should I use on the RTX 3080?
Q6_K is the highest-precision quantization that fits entirely in VRAM at 8K context. ~8.6 GB / 9.7 GB.
What is the largest context on the RTX 3080?
At Q4_K_M, about 91K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Qwen3.5 9B (RTX 3080)?
We estimate 84–119 tok/s (estimate, confidence low). Based on: memory bandwidth (760 GB/s) and model size.