Skip to content
Run LLM Locally

DeepSeek R1 Distill Qwen 14B on the RTX 5080

With 16 GB of VRAM, the RTX 5080 runs DeepSeek R1 Distill Qwen 14B at Q4_K_M entirely on the GPU with an 8K context (about 11.2 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

DeepSeek R1 Distill Qwen 14B

Q4_K_M · 8K context

Excellent

The model needs about 11.2 GB and fits in the 15.5 GB available, with 4.3 GB to spare.

Your hardware
RTX 5080 16 GB · 64 GB RAM
Estimated memory
~11.2 GB estimate
VRAM (usable memory)
15.5 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
62–89 tok/s estimate
Largest context in fast memory
29K tokens
Confidence: low

Based on: memory bandwidth (960 GB/s) and model size

Memory breakdown

~11.2 GB (10.7 GB–11.8 GB) needed · estimate

Fits entirely in VRAM · 4.3 GB left

  • Model weights8.4 GB
  • KV cache1.5 GB
  • Runtime overhead0.8 GB
  • Safety margin0.5 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 5080

DeepSeek R1 Distill Qwen 14B on RTX 5080 + 64 GB RAM · 8K context
DeepSeek R1 Distill Qwen 14B Q8_08K~17.8 GB · 7.5–14 tok/s estimateCPU/GPU offload
DeepSeek R1 Distill Qwen 14B Q6_K8K~14.3 GB · 49–69 tok/s estimateCompatible
DeepSeek R1 Distill Qwen 14B Q5_K_M8K~12.7 GB · 55–78 tok/s estimateExcellent
DeepSeek R1 Distill Qwen 14B Q4_K_M8K~11.2 GB · 62–89 tok/s estimateExcellent
DeepSeek R1 Distill Qwen 14B IQ4_XS8K~10.4 GB · 67–96 tok/s estimateExcellent
DeepSeek R1 Distill Qwen 14B Q3_K_M8K~9.6 GB · 72–105 tok/s estimateExcellent

Alternatives

GPUs that run DeepSeek R1 Distill Qwen 14B Q4_K_M entirely in VRAM

Other models that fit the RTX 5080

Where to buy a RTX 5080

Prices and links follow the market you choose.

GeForce RTX 5080

16 GB GDDR7 · 960 GB/s · 360 W

ExcellentRuns DeepSeek R1 Distill Qwen 14B 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 5080 run DeepSeek R1 Distill Qwen 14B?
The model needs about 11.2 GB and fits in the 15.5 GB available, with 4.3 GB to spare.
Which quantization should I use on the RTX 5080?
Q6_K is the highest-precision quantization that fits entirely in VRAM at 8K context. ~14.3 GB / 15.5 GB.
What is the largest context on the RTX 5080?
At Q4_K_M, about 29K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is DeepSeek R1 Distill Qwen 14B (RTX 5080)?
We estimate 62–89 tok/s (estimate, confidence low). Based on: memory bandwidth (960 GB/s) and model size.