deepseek-ai · observed 19 Oct 2026

Public-source support evidence

DeepSeek-V4.1-Flash-1017

deepseek-ai/DeepSeek-V4.1-Flash-1017

No description recorded in this snapshot.

View source model ↗

SUPPORT EVIDENCE

Runtime status

llama.cpp

Unknown

Checked the exact model config and the runtime architecture registry; no matching declared architecture was found. This is unknown, not evidence of incompatibility.

Checked 2026-10-19 02:17 UTC

Checked source ↗

Ollama

Unknown

Ollama exposes the exact deepseek-v4.1-flash:1017-cloud cloud variant; local model availability remains unknown.

Checked 2026-10-19 10:01 UTC

Checked source ↗

LM Studio

Unknown

Fresh LM Studio page identifies this model as cloud-only; local model availability remains unknown.

Checked 2026-10-19 10:01 UTC

Checked source ↗

MLX / mlx-lm

Upload available

Fresh exact base_model-tagged public repository contains weight files in a format used by mlx_lm. This establishes upload availability only; model compatibility and execution were not tested.

Checked 2026-10-19 10:01 UTC

Evidence source ↗

vLLM

Architecture listed

The model config architecture is listed in this runtime registry. This is family/architecture evidence only; exact checkpoint loading, model-specific configuration, hardware, and generation were not tested.

Checked 2026-10-19 02:17 UTC

Evidence source ↗

MLX community uploads may target mlx-vlm; an upload observation does not establish mlx-lm compatibility.

MEMORY ESTIMATES

Which file should I grab?

16 GB memory

Which file should I grab?

No observed complete artifact currently qualifies.

Unknown: no observed complete artifact fits this capacity with documented headroom.

24 GB memory

Which file should I grab?

No observed complete artifact currently qualifies.

Unknown: no observed complete artifact fits this capacity with documented headroom.

32 GB memory

Which file should I grab?

No observed complete artifact currently qualifies.

Unknown: no observed complete artifact fits this capacity with documented headroom.

128 GB memory

Which file should I grab?

No observed complete artifact currently qualifies.

Unknown: no observed complete artifact fits this capacity with documented headroom.

Observed artifact size plus 20% headroom and 1.5 GB runtime allowance. Fit is an estimate; it does not establish runtime compatibility, speed, context length, or hardware performance. Text-weights-only estimates do not include a projector or total vision memory where unknown.

OBSERVED FILES

Quant uploads

Sizes and file groups come from the listed uploader repositories. A size is marked as an estimated fit only for a complete observed GGUF quant group.

Uploader	Format & quant	Observed size	Estimated fit	Files
unslothunsloth/DeepSeek-V4.1-Flash-1017-GGUF ↗Observed 19 Oct 2026	GGUF · UD-Q4_K_XL	500.7 GB	Over 128 GBEstimated requirement exceeds 128 GB using the documented headroom formula.	9 files UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00001-of-00009.gguf5.8 MB UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00002-of-00009.gguf48.1 GB UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00003-of-00009.gguf48.1 GB UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00004-of-00009.gguf48.1 GB UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00005-of-00009.gguf48.1 GB UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00006-of-00009.gguf48.1 GB UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00007-of-00009.gguf48.1 GB UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00008-of-00009.gguf202.8 GB UD-Q4_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q4_K_XL-00009-of-00009.gguf9.2 GB Complete observed GGUF quant group; all 9 shard(s) are required.
unslothunsloth/DeepSeek-V4.1-Flash-1017-GGUF ↗Observed 19 Oct 2026	GGUF · UD-Q8_K_XL	508.4 GB	Over 128 GBEstimated requirement exceeds 128 GB using the documented headroom formula.	9 files UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00001-of-00009.gguf5.8 MB UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00002-of-00009.gguf50.5 GB UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00003-of-00009.gguf50.5 GB UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00004-of-00009.gguf50.5 GB UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00005-of-00009.gguf50.5 GB UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00006-of-00009.gguf50.5 GB UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00007-of-00009.gguf36.1 GB UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00008-of-00009.gguf202.8 GB UD-Q8_K_XL/DeepSeek-V4.1-Flash-1017-UD-Q8_K_XL-00009-of-00009.gguf16.8 GB Complete observed GGUF quant group; all 9 shard(s) are required.
mlx-communitymlx-community/DeepSeek-V4.1-Flash-1017-oQ4e-mtp ↗Observed 19 Oct 2026	MLX · Quant unknown	Size unknown	UnknownUnknown: completeness or a complete GGUF quant group was not verified.	82 files model-00001-of-00082.safetensors61.4 GB model-00002-of-00082.safetensors61.4 GB model-00003-of-00082.safetensors3.6 GB model-00004-of-00082.safetensors5.0 GB model-00005-of-00082.safetensors2.6 GB model-00006-of-00082.safetensors5.0 GB model-00007-of-00082.safetensors4.8 GB model-00008-of-00082.safetensors2.6 GB model-00009-of-00082.safetensors4.8 GB model-00010-of-00082.safetensors2.6 GB model-00011-of-00082.safetensors4.8 GB model-00012-of-00082.safetensors3.9 GB model-00013-of-00082.safetensors4.8 GB model-00014-of-00082.safetensors2.6 GB model-00015-of-00082.safetensors4.8 GB model-00016-of-00082.safetensors2.6 GB model-00017-of-00082.safetensors4.8 GB model-00018-of-00082.safetensors2.6 GB model-00019-of-00082.safetensors4.8 GB model-00020-of-00082.safetensors2.6 GB model-00021-of-00082.safetensors4.8 GB model-00022-of-00082.safetensors2.6 GB model-00023-of-00082.safetensors4.8 GB model-00024-of-00082.safetensors2.6 GB model-00025-of-00082.safetensors4.8 GB model-00026-of-00082.safetensors2.6 GB model-00027-of-00082.safetensors4.8 GB model-00028-of-00082.safetensors2.6 GB model-00029-of-00082.safetensors4.8 GB model-00030-of-00082.safetensors2.6 GB model-00031-of-00082.safetensors4.8 GB model-00032-of-00082.safetensors4.1 GB model-00033-of-00082.safetensors4.8 GB model-00034-of-00082.safetensors2.6 GB model-00035-of-00082.safetensors4.8 GB model-00036-of-00082.safetensors2.6 GB model-00037-of-00082.safetensors4.8 GB model-00038-of-00082.safetensors2.6 GB model-00039-of-00082.safetensors4.8 GB model-00040-of-00082.safetensors2.6 GB model-00041-of-00082.safetensors4.8 GB model-00042-of-00082.safetensors4.2 GB model-00043-of-00082.safetensors3.5 GB model-00044-of-00082.safetensors5.0 GB model-00045-of-00082.safetensors4.8 GB model-00046-of-00082.safetensors2.6 GB model-00047-of-00082.safetensors4.8 GB model-00048-of-00082.safetensors2.6 GB model-00049-of-00082.safetensors4.8 GB model-00050-of-00082.safetensors2.6 GB model-00051-of-00082.safetensors4.8 GB model-00052-of-00082.safetensors4.2 GB model-00053-of-00082.safetensors3.4 GB model-00054-of-00082.safetensors5.0 GB model-00055-of-00082.safetensors4.8 GB model-00056-of-00082.safetensors2.6 GB model-00057-of-00082.safetensors4.8 GB model-00058-of-00082.safetensors2.6 GB model-00059-of-00082.safetensors4.8 GB model-00060-of-00082.safetensors2.6 GB model-00061-of-00082.safetensors4.8 GB model-00062-of-00082.safetensors4.2 GB model-00063-of-00082.safetensors3.5 GB model-00064-of-00082.safetensors5.0 GB model-00065-of-00082.safetensors4.8 GB model-00066-of-00082.safetensors2.6 GB model-00067-of-00082.safetensors4.8 GB model-00068-of-00082.safetensors2.6 GB model-00069-of-00082.safetensors4.8 GB model-00070-of-00082.safetensors2.6 GB model-00071-of-00082.safetensors4.8 GB model-00072-of-00082.safetensors2.6 GB model-00073-of-00082.safetensors4.8 GB model-00074-of-00082.safetensors2.6 GB model-00075-of-00082.safetensors4.8 GB model-00076-of-00082.safetensors2.6 GB model-00077-of-00082.safetensors4.8 GB model-00078-of-00082.safetensors2.6 GB model-00079-of-00082.safetensors4.8 GB model-00080-of-00082.safetensors2.6 GB model-00081-of-00082.safetensors4.8 GB model-00082-of-00082.safetensors2.4 GB Observed weight file metadata; completeness unavailable without index/config verification.
mlx-communitymlx-community/DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp ↗Observed 19 Oct 2026	MLX · Quant unknown	Size unknown	UnknownUnknown: completeness or a complete GGUF quant group was not verified.	53 files model-00001-of-00053.safetensors61.4 GB model-00002-of-00053.safetensors61.4 GB model-00003-of-00053.safetensors4.0 GB model-00004-of-00053.safetensors4.3 GB model-00005-of-00053.safetensors4.2 GB model-00006-of-00053.safetensors5.0 GB model-00007-of-00053.safetensors5.0 GB model-00008-of-00053.safetensors4.9 GB model-00009-of-00053.safetensors4.4 GB model-00010-of-00053.safetensors4.2 GB model-00011-of-00053.safetensors4.2 GB model-00012-of-00053.safetensors5.0 GB model-00013-of-00053.safetensors5.0 GB model-00014-of-00053.safetensors4.0 GB model-00015-of-00053.safetensors3.6 GB model-00016-of-00053.safetensors3.6 GB model-00017-of-00053.safetensors5.0 GB model-00018-of-00053.safetensors4.0 GB model-00019-of-00053.safetensors3.6 GB model-00020-of-00053.safetensors3.6 GB model-00021-of-00053.safetensors4.8 GB model-00022-of-00053.safetensors4.5 GB model-00023-of-00053.safetensors3.6 GB model-00024-of-00053.safetensors3.6 GB model-00025-of-00053.safetensors4.0 GB model-00026-of-00053.safetensors3.6 GB model-00027-of-00053.safetensors3.6 GB model-00028-of-00053.safetensors5.0 GB model-00029-of-00053.safetensors4.1 GB model-00030-of-00053.safetensors3.6 GB model-00031-of-00053.safetensors5.0 GB model-00032-of-00053.safetensors4.0 GB model-00033-of-00053.safetensors3.6 GB model-00034-of-00053.safetensors3.6 GB model-00035-of-00053.safetensors5.0 GB model-00036-of-00053.safetensors4.1 GB model-00037-of-00053.safetensors3.6 GB model-00038-of-00053.safetensors5.0 GB model-00039-of-00053.safetensors5.0 GB model-00040-of-00053.safetensors5.0 GB model-00041-of-00053.safetensors5.0 GB model-00042-of-00053.safetensors4.4 GB model-00043-of-00053.safetensors3.6 GB model-00044-of-00053.safetensors5.0 GB model-00045-of-00053.safetensors5.0 GB model-00046-of-00053.safetensors5.0 GB model-00047-of-00053.safetensors5.0 GB model-00048-of-00053.safetensors3.0 GB model-00049-of-00053.safetensors3.6 GB model-00050-of-00053.safetensors3.6 GB model-00051-of-00053.safetensors5.0 GB model-00052-of-00053.safetensors5.0 GB model-00053-of-00053.safetensors4.9 GB Observed weight file metadata; completeness unavailable without index/config verification.

CURATED TRACKING

Known issues

No curated issues verified for this snapshot. An empty list does not mean there are no bugs.

HARDWARE NOTES

Tested on DGX Spark / Mac Studio: coming soon

No hardware benchmark measurements are available in this snapshot.