model
DeepSeek V4.1 Flash 1017: how much memory, and what runs it
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.
DeepSeek V4.1 Flash 1017 needs about 445.5 GB at Q4_K_M with 8K context (estimate). See which GPUs and Macs fit it, and EU prices. Speed is not estimated for this mixture-of-experts model.
| Quantisation | Estimated memory |
|---|---|
| Q4 | 445.5 GBestimate |
| Q5 | 392.6 GBestimate |
| Q8 | 591.3 GBestimate |
| FP16 | 1,104.6 GBestimate |
At 8,192 tokens of context. Catalog quant rates are a formula. sourceUrl on that memory stays null.
KV cache not modelled for this architecture: real use needs more than the figures shown
Parameter count source: huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash. 551.9B total, 16B active. Memory math uses the total.
VRAM per quant and the cheapest rig for DeepSeek V4.1 Flash 1017
Three setups
DeepSeek V4.1 Flash 1017 · Q4 · 8,192 ctx
Estimated memory
445.5 GBestimate
444.7 GB weights · 0.0 GB KV cache · 0.8 GB overhead
Nothing in this dataset can run this model, not even with CPU offload.
Tokens per second are estimated from memory bandwidth, not from a measured benchmark. Prices incl. VAT, excl. shipping. USD = FX estimate, excl. sales tax. A price without a checked listing is marked price unverified. Run llama-bench yourself before you buy.
Want a build tailored to you? Custom report
Get new builds when GPU prices move
End of results
Embed this
[](https://localllmrig.com/can-i-run/deepseek-v4.1-flash-1017/rtx-3060-12gb?utm_source=badge)
Model badge
[](https://localllmrig.com/models/deepseek-v4.1-flash-1017?utm_source=badge)
Common questions
- How much memory does DeepSeek V4.1 Flash 1017 need at Q4?
- About 445.5 GB at 8,192 tokens: 444.7 GB weights, KV cache not modelled (the 0 GB figure is not a cache estimate), 0.8 GB overhead. The total is an estimate and real use needs more. sourceUrl stays null.
- Does DeepSeek V4.1 Flash 1017 fit on a single 24 GB GPU?
- Not in full. The estimate is 445.5 GB, and a 24 GB card leaves 23.4 GB usable. sourceUrl stays null.
- Are the tokens per second measured?
- speed: not estimated for MoE yet