estimate
Can I run DeepSeek V4.1 Flash 1017 on an RX 7900 XTX?
No: needs ~445.5 GB, this card has ~23.4 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 RX 7900 XTX? No: needs ~445.5 GB, this card has ~23.4 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 | 23.4 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 | 23.4 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 | 23.4 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 | 23.4 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 | 23.4 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
$1,404€1,254
used (3-month median)
price as of 17 Oct 2026
new in stock, €3,972 at GPU PRIX on 17 Oct 2026 (unusually high): $4,447€3,972. GPU PRIX. More than 1.5× the €1,254 3-month median, so this listing is not the headline.
GPU PRIXChecked GPU PRIX on 17 Oct 2026. The page says last updated Oct 17, 2026. The 3-month median is €1,254. The only in-stock board, ASUS TUF Gaming RX 7900 XTX at €3,972, is more than 1.5× that median, so the median is the stored price. The header current low of €43 is a DisplayPort cable, not the card. XFX Speedster was €1,049 and out of stock. MSI Gaming Trio €3,047 and POWERCOLOR Red Devil €3,152 were out of stock. On 16 Oct 2026 the stored new figure was the out-of-stock price, about €1,050. 12-month median €1,101. Not a pcprice.watch sold-listing median.
Embed this
DeepSeek V4.1 Flash 1017 on RX 7900 XTX
[](https://localllmrig.com/can-i-run/deepseek-v4.1-flash-1017/rx-7900-xtx?utm_source=badge)
Questions
- Can I run DeepSeek V4.1 Flash 1017 on an RX 7900 XTX?
- No: needs ~445.5 GB, this card has ~23.4 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 RX 7900 XTX (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.