estimate
Can I run DeepSeek V4.1 Flash 1017 on an RTX 5080?
No: needs ~445.5 GB, this card has ~15.4 GB usable (estimate)
speed: not estimated for MoE yet
KV cache not modelled for this architecture: real use needs more than the figures shown
MLX: Apple Silicon only
Mainline llama.cpp does not support DeepSeek V4.1 yet (open PR https://github.com/ggml-org/llama.cpp/pull/28696, checked 17 Oct 2026); the community GGUFs need that branch and are text-only. Ollama offers deepseek-v4.1-flash:cloud only (no local tag, https://ollama.com/library/deepseek-v4.1-flash). Official weights: FP8 with FP4 experts, 510.3 GB on HF. Language backbone stored as 551.9B; the architecture section says "552B backbone parameters" (1017 is a minor update of https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash). Weights for this row: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017. Also 196.6B Engram conditional-memory parameters (sparse token lookup), 14.2B MTP head and 0.49B vision encoder. Total logical weights 763.2B (HF safetensors metadata). Causal encoder-decoder, 40 layers (20 encoder + 20 decoder), 384 routed experts plus 1 shared, 6 routed per token, CSA2 compressed attention. KV is projected from encoder states with compressed and sliding attention (persistent KV about 1/8 of V4-Flash); this catalog does not compute that cache.
Can I run DeepSeek V4.1 Flash 1017 on an RTX 5080? No: needs ~445.5 GB, this card has ~15.4 GB usable (estimate). About 445.5 GB at Q4_K_M (estimate).
VRAM per quant for DeepSeek V4.1 Flash 1017
Updated . The later of the hardware price date and the formula date.
| Quant | Context | Weights | KV | Overhead | Total | Usable | Fit |
|---|---|---|---|---|---|---|---|
| Q4 Q4_K_M | 8,192 tokens | 444.7 GB measured GGUF file size | 0.0 GB not modelled | 0.8 GB estimate | 445.5 GB estimate | 15.4 GB estimate | no |
| Q5 Q5 (~0.71 bytes/param) | 8,192 tokens | 391.8 GB estimate | 0.0 GB not modelled | 0.8 GB estimate | 392.6 GB estimate | 15.4 GB estimate | no |
| Q8 Q8 | 8,192 tokens | 590.5 GB estimate | 0.0 GB not modelled | 0.8 GB estimate | 591.3 GB estimate | 15.4 GB estimate | no |
| FP16 FP16 | 8,192 tokens | 1,103.8 GB estimate | 0.0 GB not modelled | 0.8 GB estimate | 1,104.6 GB estimate | 15.4 GB estimate | no |
| Q4, longer context | 32,768 tokens | 444.7 GB measured GGUF file size | 0.0 GB not modelled | 0.8 GB estimate | 445.5 GB estimate | 15.4 GB estimate | no |
Formula estimate, not a benchmark. Method →
Cheapest catalog option that fits at Q4
No catalog row fully fits at Q4 (estimate).
This hardware
$1,468€1,311
new (lowest in-stock EU)
price as of 17 Oct 2026
GPU PRIXLowest in-stock board in the table on 17 Oct 2026: €1,311, ASUS Prime GeForce RTX 5080, in stock. The same page's header current low was €1,328, last updated Oct 17, 2026. 16 GB GDDR7 and 360 W total graphics power are on NVIDIA's RTX 5080 spec page (https://www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5080/). 960 GB/sec is the RTX 5080 column on NVIDIA's GeForce compare page (https://www.nvidia.com/en-us/geforce/graphics-cards/compare/). The product spec table that was fetched did not print a GB/s row.
Embed this
DeepSeek V4.1 Flash 1017 on RTX 5080
[](https://localllmrig.com/can-i-run/deepseek-v4.1-flash-1017/rtx-5080?utm_source=badge)
Questions
- Can I run DeepSeek V4.1 Flash 1017 on an RTX 5080?
- No: needs ~445.5 GB, this card has ~15.4 GB usable (estimate).
- How much memory does DeepSeek V4.1 Flash 1017 need at Q4?
- About 445.5 GB at 8,192 tokens (estimate): 444.7 GB weights (measured GGUF file size), 0.0 GB KV cache (not modelled; real use needs more), 0.8 GB overhead.
- How fast is DeepSeek V4.1 Flash 1017 on RTX 5080 (estimate)?
- speed: not estimated for MoE yet
Rig Report waitlist
A written hardware plan for one model and budget. Planned price, not for sale yet.
Sign up with consent and download GPU Buying Cheat Sheet (EU, Oct 2026). The file is not emailed.
Read next: Building a local LLM rig in the RAMageddon.