# Request to Add DeepSeek-V4.1-Flash-1017 to NVIDIA NIM

**URL:** <https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307>\
**Category:** Models\
**Tags:** deepseek, nim\
**Created:** [October 19, 2026, 10:35am UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307 "2026-10-19T10:35:31Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![yourmomdead12](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@yourmomdead12](https://forums.developer.nvidia.com/u/yourmomdead12)\
**Post date:** [October 19, 2026, 10:35am UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307/1 "2026-10-19T10:35:31Z")

</div>

DeepSeek open-sourced DeepSeek-V4.1-Flash-1017 on October 17, 2026, under the MIT License. The weights are available on Hugging Face and ModelScope. The model permits commercial use, and the vLLM and SGLang communities already provide support. We request that it be added to the NVIDIA NIM API.

---

<div class="post-metadata">

**Author:** ![supervisorxscp](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/supervisorxscp/32/510296_2.png) [@supervisorxscp](https://forums.developer.nvidia.com/u/supervisorxscp)\
**Post date:** [October 19, 2026, 11:40am UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307/2 "2026-10-19T11:40:51Z")

</div>

It may come in next 1-2 week cause dev team need to test its compatibility and performance

---

<div class="post-metadata">

**Author:** ![tigrass83](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@tigrass83](https://forums.developer.nvidia.com/u/tigrass83)\
**Post date:** [October 19, 2026, 6:30pm UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307/4 "2026-10-19T18:30:31Z")

</div>

OMG, their old version hasn’t been working for days now, and you’re asking for a new one)

---

<div class="post-metadata">

**Author:** ![supervisorxscp](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/supervisorxscp/32/510296_2.png) [@supervisorxscp](https://forums.developer.nvidia.com/u/supervisorxscp)\
**Post date:** [October 21, 2026, 5:28am UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307/5 "2026-10-21T05:28:38Z")

</div>

it worked fine for me, fast and good

---

<div class="post-metadata">

**Author:** ![tigrass83](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@tigrass83](https://forums.developer.nvidia.com/u/tigrass83)\
**Post date:** [October 21, 2026, 5:31am UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307/6 "2026-10-21T05:31:48Z")

</div>

For the first time in a week, I see that the model is responding, though very slowly.

---

<div class="post-metadata">

**Author:** ![supervisorxscp](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/supervisorxscp/32/510296_2.png) [@supervisorxscp](https://forums.developer.nvidia.com/u/supervisorxscp)\
**Post date:** [October 21, 2026, 1:13pm UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307/7 "2026-10-21T13:13:34Z")

</div>

Me is normal:

- average tps: ~40 T/S
- Average time to first token: 8-40 sec
- Highest tps: ~60-70 t/s

---

<div class="post-metadata">

**Author:** ![tigrass83](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@tigrass83](https://forums.developer.nvidia.com/u/tigrass83)\
**Post date:** [October 21, 2026, 1:15pm UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307/8 "2026-10-21T13:15:29Z")

</div>

Maybe it depends on the location? I’m in Germany, and it’s very slow.

---

<div class="post-metadata">

**Author:** ![supervisorxscp](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/supervisorxscp/32/510296_2.png) [@supervisorxscp](https://forums.developer.nvidia.com/u/supervisorxscp)\
**Post date:** [October 22, 2026, 11:43am UTC](https://forums.developer.nvidia.com/t/request-to-add-deepseek-v4-1-flash-1017-to-nvidia-nim/386307/9 "2026-10-22T11:43:09Z")

</div>

Maybe but now deepseek-v4.1 is heavily limited  
always 429 errors but others work fine