deepseek-ai · Released Dec 25, 2024 · observed 28 Oct 2026

Public-source support evidence

DeepSeek-V3

DeepSeek-V3 is listed for local download in Ollama. A separately observed community Q4_K_M GGUF gives an estimated memory budget of about 487 GB; actual use depends on runtime and context settings.

deepseek-ai/DeepSeek-V3

DeepSeek-V3 is a text generation model published by deepseek-ai on Hugging Face. We have not written a summary yet; see the model card ↗.

View source model ↗

SUPPORT EVIDENCE

Runtime status

llama.cpp

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 2026-10-28 10:02 UTC

Evidence source ↗

Ollama

In release

In release. Ollama public library page exposes this exact size variant; catalog availability only, not hardware-tested support.

Checked 2026-10-28 10:09 UTC

Evidence source ↗

LM Studio

Unknown

The exact model and runtime-specific sources were checked; no positive model-level evidence was established.

Checked 2026-10-28 10:00 UTC

Checked source ↗

MLX / mlx-lm

Upload available

A current public MLX upload with an exact base_model match was observed. Upload availability only; this model was not loaded or hardware-tested.

Checked 2026-10-28 10:09 UTC

Evidence source ↗

vLLM

Architecture listed

Checked 2026-10-28 10:02 UTC

Evidence source ↗

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

Which file should I grab?

Q4_K_M · 404.4 GB observed · about 487 GB ↗

About 487 GB using file size × 1.2 + 1.5 GB. Fit is an estimate; compatibility, speed, context length and hardware have not been tested. Link points to shard 1; all 9 linked shards are required.

Memory estimates are the observed file size plus fixed headroom (20% plus 1.5 GB runtime allowance); real needs also depend on context length, KV cache and runtime settings. 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.

Terms: a quant is a lower-precision version of the weights; GGUF is a file format used by llama.cpp and compatible apps; MLX targets Apple silicon; vLLM is a model-serving engine for NVIDIA GPUs; the KV cache is stored attention state that grows with context length. Terms explained ↗

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-V3-GGUF ↗Observed 28 Oct 2026	GGUF · Q2_K_L	244.2 GB	512 GBEstimate only; requires the complete GGUF quant group.	5 files DeepSeek-V3-Q2_K_L/DeepSeek-V3-Q2_K_L-00001-of-00005.gguf49.6 GB DeepSeek-V3-Q2_K_L/DeepSeek-V3-Q2_K_L-00002-of-00005.gguf48.5 GB DeepSeek-V3-Q2_K_L/DeepSeek-V3-Q2_K_L-00003-of-00005.gguf48.8 GB DeepSeek-V3-Q2_K_L/DeepSeek-V3-Q2_K_L-00004-of-00005.gguf48.9 GB DeepSeek-V3-Q2_K_L/DeepSeek-V3-Q2_K_L-00005-of-00005.gguf48.4 GB Complete observed GGUF quant group; all 5 shard(s) are required.
unslothunsloth/DeepSeek-V3-GGUF ↗Observed 28 Oct 2026	GGUF · Q2_K_XS	221.3 GB	512 GBEstimate only; requires the complete GGUF quant group.	5 files DeepSeek-V3-Q2_K_XS/DeepSeek-V3-Q2_K_XS-00001-of-00005.gguf44.8 GB DeepSeek-V3-Q2_K_XS/DeepSeek-V3-Q2_K_XS-00002-of-00005.gguf44.2 GB DeepSeek-V3-Q2_K_XS/DeepSeek-V3-Q2_K_XS-00003-of-00005.gguf44.1 GB DeepSeek-V3-Q2_K_XS/DeepSeek-V3-Q2_K_XS-00004-of-00005.gguf44.1 GB DeepSeek-V3-Q2_K_XS/DeepSeek-V3-Q2_K_XS-00005-of-00005.gguf44.1 GB Complete observed GGUF quant group; all 5 shard(s) are required.
unslothunsloth/DeepSeek-V3-GGUF ↗Observed 28 Oct 2026	GGUF · Q3_K_M	319.2 GB	512 GBEstimate only; requires the complete GGUF quant group.	7 files DeepSeek-V3-Q3_K_M/DeepSeek-V3-Q3_K_M-00001-of-00007.gguf45.9 GB DeepSeek-V3-Q3_K_M/DeepSeek-V3-Q3_K_M-00002-of-00007.gguf45.9 GB DeepSeek-V3-Q3_K_M/DeepSeek-V3-Q3_K_M-00003-of-00007.gguf47.0 GB DeepSeek-V3-Q3_K_M/DeepSeek-V3-Q3_K_M-00004-of-00007.gguf46.0 GB DeepSeek-V3-Q3_K_M/DeepSeek-V3-Q3_K_M-00005-of-00007.gguf47.0 GB DeepSeek-V3-Q3_K_M/DeepSeek-V3-Q3_K_M-00006-of-00007.gguf46.0 GB DeepSeek-V3-Q3_K_M/DeepSeek-V3-Q3_K_M-00007-of-00007.gguf41.5 GB Complete observed GGUF quant group; all 7 shard(s) are required.
unslothunsloth/DeepSeek-V3-GGUF ↗Observed 28 Oct 2026	GGUF · Q4_K_M	404.4 GB	512 GBEstimate only; requires the complete GGUF quant group.	9 files DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00001-of-00009.gguf45.2 GB DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00002-of-00009.gguf46.0 GB DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00003-of-00009.gguf45.2 GB DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00004-of-00009.gguf45.2 GB DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00005-of-00009.gguf45.1 GB DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00006-of-00009.gguf46.1 GB DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00007-of-00009.gguf45.2 GB DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00008-of-00009.gguf44.9 GB DeepSeek-V3-Q4_K_M/DeepSeek-V3-Q4_K_M-00009-of-00009.gguf41.5 GB Complete observed GGUF quant group; all 9 shard(s) are required.
unslothunsloth/DeepSeek-V3-GGUF ↗Observed 28 Oct 2026	GGUF · Q5_K_M	475.4 GB	Over 512 GBEstimated requirement exceeds 512 GB using the documented headroom formula.	10 files DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00001-of-00010.gguf49.6 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00002-of-00010.gguf48.5 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00003-of-00010.gguf48.5 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00004-of-00010.gguf48.5 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00005-of-00010.gguf48.5 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00006-of-00010.gguf48.5 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00007-of-00010.gguf48.5 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00008-of-00010.gguf48.5 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00009-of-00010.gguf50.0 GB DeepSeek-V3-Q5_K_M/DeepSeek-V3-Q5_K_M-00010-of-00010.gguf36.3 GB Complete observed GGUF quant group; all 10 shard(s) are required.
unslothunsloth/DeepSeek-V3-GGUF ↗Observed 28 Oct 2026	GGUF · Q6_K	550.8 GB	Over 512 GBEstimated requirement exceeds 512 GB using the documented headroom formula.	12 files DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00001-of-00012.gguf47.1 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00002-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00003-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00004-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00005-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00006-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00007-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00008-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00009-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00010-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00011-of-00012.gguf47.2 GB DeepSeek-V3-Q6_K/DeepSeek-V3-Q6_K-00012-of-00012.gguf31.4 GB Complete observed GGUF quant group; all 12 shard(s) are required.
unslothunsloth/DeepSeek-V3-GGUF ↗Observed 28 Oct 2026	GGUF · Q8_0	713.3 GB	Over 512 GBEstimated requirement exceeds 512 GB using the documented headroom formula.	16 files DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00001-of-00016.gguf43.8 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00002-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00003-of-00016.gguf44.7 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00004-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00005-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00006-of-00016.gguf44.7 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00007-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00008-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00009-of-00016.gguf44.7 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00010-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00011-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00012-of-00016.gguf44.7 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00013-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00014-of-00016.gguf44.9 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00015-of-00016.gguf44.7 GB DeepSeek-V3-Q8_0/DeepSeek-V3-BF16-256x20B-Q8_0-00016-of-00016.gguf41.7 GB Complete observed GGUF quant group; all 16 shard(s) are required.
mlx-communitymlx-community/DeepSeek-V3-3bit ↗Observed 28 Oct 2026	MLX · Quant unknown	Size unknown	UnknownUnknown: completeness or a complete GGUF quant group was not verified.	70 files model-00001-of-00070.safetensors5.2 GB model-00002-of-00070.safetensors5.3 GB model-00003-of-00070.safetensors4.3 GB model-00004-of-00070.safetensors5.3 GB model-00005-of-00070.safetensors4.3 GB model-00006-of-00070.safetensors5.2 GB model-00007-of-00070.safetensors4.3 GB model-00008-of-00070.safetensors5.3 GB model-00009-of-00070.safetensors4.3 GB model-00010-of-00070.safetensors5.3 GB model-00011-of-00070.safetensors4.3 GB model-00012-of-00070.safetensors5.2 GB model-00013-of-00070.safetensors4.3 GB model-00014-of-00070.safetensors5.3 GB model-00015-of-00070.safetensors4.3 GB model-00016-of-00070.safetensors5.3 GB model-00017-of-00070.safetensors4.3 GB model-00018-of-00070.safetensors5.2 GB model-00019-of-00070.safetensors4.3 GB model-00020-of-00070.safetensors5.3 GB model-00021-of-00070.safetensors4.3 GB model-00022-of-00070.safetensors5.3 GB model-00023-of-00070.safetensors4.3 GB model-00024-of-00070.safetensors5.2 GB model-00025-of-00070.safetensors4.3 GB model-00026-of-00070.safetensors5.3 GB model-00027-of-00070.safetensors4.3 GB model-00028-of-00070.safetensors5.3 GB model-00029-of-00070.safetensors4.3 GB model-00030-of-00070.safetensors5.2 GB model-00031-of-00070.safetensors4.3 GB model-00032-of-00070.safetensors5.3 GB model-00033-of-00070.safetensors4.3 GB model-00034-of-00070.safetensors5.3 GB model-00035-of-00070.safetensors4.3 GB model-00036-of-00070.safetensors5.2 GB model-00037-of-00070.safetensors4.3 GB model-00038-of-00070.safetensors5.3 GB model-00039-of-00070.safetensors4.3 GB model-00040-of-00070.safetensors5.3 GB model-00041-of-00070.safetensors4.3 GB model-00042-of-00070.safetensors5.2 GB model-00043-of-00070.safetensors4.3 GB model-00044-of-00070.safetensors5.3 GB model-00045-of-00070.safetensors4.3 GB model-00046-of-00070.safetensors5.3 GB model-00047-of-00070.safetensors4.3 GB model-00048-of-00070.safetensors5.2 GB model-00049-of-00070.safetensors4.3 GB model-00050-of-00070.safetensors5.3 GB model-00051-of-00070.safetensors4.3 GB model-00052-of-00070.safetensors5.3 GB model-00053-of-00070.safetensors4.3 GB model-00054-of-00070.safetensors5.2 GB model-00055-of-00070.safetensors4.3 GB model-00056-of-00070.safetensors5.3 GB model-00057-of-00070.safetensors4.3 GB model-00058-of-00070.safetensors5.3 GB model-00059-of-00070.safetensors4.3 GB model-00060-of-00070.safetensors5.2 GB model-00061-of-00070.safetensors4.3 GB model-00062-of-00070.safetensors5.3 GB model-00063-of-00070.safetensors4.3 GB model-00064-of-00070.safetensors5.3 GB model-00065-of-00070.safetensors4.3 GB model-00066-of-00070.safetensors5.2 GB model-00067-of-00070.safetensors4.3 GB model-00068-of-00070.safetensors5.3 GB model-00069-of-00070.safetensors4.3 GB model-00070-of-00070.safetensors4.2 GB Observed weight file metadata; completeness unavailable without index/config verification.
mlx-communitymlx-community/DeepSeek-V3-3bit-bf16 ↗Observed 28 Oct 2026	MLX · Quant unknown	Size unknown	UnknownUnknown: completeness or a complete GGUF quant group was not verified.	70 files model-00001-of-00070.safetensors5.2 GB model-00002-of-00070.safetensors5.3 GB model-00003-of-00070.safetensors4.3 GB model-00004-of-00070.safetensors5.3 GB model-00005-of-00070.safetensors4.3 GB model-00006-of-00070.safetensors5.2 GB model-00007-of-00070.safetensors4.3 GB model-00008-of-00070.safetensors5.3 GB model-00009-of-00070.safetensors4.3 GB model-00010-of-00070.safetensors5.3 GB model-00011-of-00070.safetensors4.3 GB model-00012-of-00070.safetensors5.2 GB model-00013-of-00070.safetensors4.3 GB model-00014-of-00070.safetensors5.3 GB model-00015-of-00070.safetensors4.3 GB model-00016-of-00070.safetensors5.3 GB model-00017-of-00070.safetensors4.3 GB model-00018-of-00070.safetensors5.2 GB model-00019-of-00070.safetensors4.3 GB model-00020-of-00070.safetensors5.3 GB model-00021-of-00070.safetensors4.3 GB model-00022-of-00070.safetensors5.3 GB model-00023-of-00070.safetensors4.3 GB model-00024-of-00070.safetensors5.2 GB model-00025-of-00070.safetensors4.3 GB model-00026-of-00070.safetensors5.3 GB model-00027-of-00070.safetensors4.3 GB model-00028-of-00070.safetensors5.3 GB model-00029-of-00070.safetensors4.3 GB model-00030-of-00070.safetensors5.2 GB model-00031-of-00070.safetensors4.3 GB model-00032-of-00070.safetensors5.3 GB model-00033-of-00070.safetensors4.3 GB model-00034-of-00070.safetensors5.3 GB model-00035-of-00070.safetensors4.3 GB model-00036-of-00070.safetensors5.2 GB model-00037-of-00070.safetensors4.3 GB model-00038-of-00070.safetensors5.3 GB model-00039-of-00070.safetensors4.3 GB model-00040-of-00070.safetensors5.3 GB model-00041-of-00070.safetensors4.3 GB model-00042-of-00070.safetensors5.2 GB model-00043-of-00070.safetensors4.3 GB model-00044-of-00070.safetensors5.3 GB model-00045-of-00070.safetensors4.3 GB model-00046-of-00070.safetensors5.3 GB model-00047-of-00070.safetensors4.3 GB model-00048-of-00070.safetensors5.2 GB model-00049-of-00070.safetensors4.3 GB model-00050-of-00070.safetensors5.3 GB model-00051-of-00070.safetensors4.3 GB model-00052-of-00070.safetensors5.3 GB model-00053-of-00070.safetensors4.3 GB model-00054-of-00070.safetensors5.2 GB model-00055-of-00070.safetensors4.3 GB model-00056-of-00070.safetensors5.3 GB model-00057-of-00070.safetensors4.3 GB model-00058-of-00070.safetensors5.3 GB model-00059-of-00070.safetensors4.3 GB model-00060-of-00070.safetensors5.2 GB model-00061-of-00070.safetensors4.3 GB model-00062-of-00070.safetensors5.3 GB model-00063-of-00070.safetensors4.3 GB model-00064-of-00070.safetensors5.3 GB model-00065-of-00070.safetensors4.3 GB model-00066-of-00070.safetensors5.2 GB model-00067-of-00070.safetensors4.3 GB model-00068-of-00070.safetensors5.3 GB model-00069-of-00070.safetensors4.3 GB model-00070-of-00070.safetensors4.2 GB Observed weight file metadata; completeness unavailable without index/config verification.
mlx-communitymlx-community/DeepSeek-V3-4bit ↗Observed 28 Oct 2026	MLX · Quant unknown	Size unknown	UnknownUnknown: completeness or a complete GGUF quant group was not verified.	88 files model-00001-of-00088.safetensors3.7 GB model-00002-of-00088.safetensors4.4 GB model-00003-of-00088.safetensors4.2 GB model-00004-of-00088.safetensors4.4 GB model-00005-of-00088.safetensors4.4 GB model-00006-of-00088.safetensors4.2 GB model-00007-of-00088.safetensors4.4 GB model-00008-of-00088.safetensors4.4 GB model-00009-of-00088.safetensors4.2 GB model-00010-of-00088.safetensors4.4 GB model-00011-of-00088.safetensors4.4 GB model-00012-of-00088.safetensors4.2 GB model-00013-of-00088.safetensors4.4 GB model-00014-of-00088.safetensors4.4 GB model-00015-of-00088.safetensors4.2 GB model-00016-of-00088.safetensors4.4 GB model-00017-of-00088.safetensors4.4 GB model-00018-of-00088.safetensors4.2 GB model-00019-of-00088.safetensors4.4 GB model-00020-of-00088.safetensors4.4 GB model-00021-of-00088.safetensors4.2 GB model-00022-of-00088.safetensors4.4 GB model-00023-of-00088.safetensors4.4 GB model-00024-of-00088.safetensors4.2 GB model-00025-of-00088.safetensors4.4 GB model-00026-of-00088.safetensors4.4 GB model-00027-of-00088.safetensors4.2 GB model-00028-of-00088.safetensors4.4 GB model-00029-of-00088.safetensors4.4 GB model-00030-of-00088.safetensors4.2 GB model-00031-of-00088.safetensors4.4 GB model-00032-of-00088.safetensors4.4 GB model-00033-of-00088.safetensors4.2 GB model-00034-of-00088.safetensors4.4 GB model-00035-of-00088.safetensors4.4 GB model-00036-of-00088.safetensors4.2 GB model-00037-of-00088.safetensors4.4 GB model-00038-of-00088.safetensors4.4 GB model-00039-of-00088.safetensors4.2 GB model-00040-of-00088.safetensors4.4 GB model-00041-of-00088.safetensors4.4 GB model-00042-of-00088.safetensors4.2 GB model-00043-of-00088.safetensors4.4 GB model-00044-of-00088.safetensors4.4 GB model-00045-of-00088.safetensors4.2 GB model-00046-of-00088.safetensors4.4 GB model-00047-of-00088.safetensors4.4 GB model-00048-of-00088.safetensors4.2 GB model-00049-of-00088.safetensors4.4 GB model-00050-of-00088.safetensors4.4 GB model-00051-of-00088.safetensors4.2 GB model-00052-of-00088.safetensors4.4 GB model-00053-of-00088.safetensors4.4 GB model-00054-of-00088.safetensors4.2 GB model-00055-of-00088.safetensors4.4 GB model-00056-of-00088.safetensors4.4 GB model-00057-of-00088.safetensors4.2 GB model-00058-of-00088.safetensors4.4 GB model-00059-of-00088.safetensors4.4 GB model-00060-of-00088.safetensors4.2 GB model-00061-of-00088.safetensors4.4 GB model-00062-of-00088.safetensors4.4 GB model-00063-of-00088.safetensors4.2 GB model-00064-of-00088.safetensors4.4 GB model-00065-of-00088.safetensors4.4 GB model-00066-of-00088.safetensors4.2 GB model-00067-of-00088.safetensors4.4 GB model-00068-of-00088.safetensors4.4 GB model-00069-of-00088.safetensors4.2 GB model-00070-of-00088.safetensors4.4 GB model-00071-of-00088.safetensors4.4 GB model-00072-of-00088.safetensors4.2 GB model-00073-of-00088.safetensors4.4 GB model-00074-of-00088.safetensors4.4 GB model-00075-of-00088.safetensors4.2 GB model-00076-of-00088.safetensors4.4 GB model-00077-of-00088.safetensors4.4 GB model-00078-of-00088.safetensors4.2 GB model-00079-of-00088.safetensors4.4 GB model-00080-of-00088.safetensors4.4 GB model-00081-of-00088.safetensors4.2 GB model-00082-of-00088.safetensors4.4 GB model-00083-of-00088.safetensors4.4 GB model-00084-of-00088.safetensors4.2 GB model-00085-of-00088.safetensors4.4 GB model-00086-of-00088.safetensors4.4 GB model-00087-of-00088.safetensors4.2 GB model-00088-of-00088.safetensors2.7 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

Hardware testing planned

No execution or benchmark results are published for this model yet.

COMPARE

Compare with…

Browse all comparisons →

EMBED

Embed this badge

Markdown

[![Runs local: Ollama ✓ · ~487 GB](https://doesitrunlocal.com/badge/deepseek-ai-deepseek-v3.svg)](https://doesitrunlocal.com/models/deepseek-ai-deepseek-v3/)

HTML

<a href="https://doesitrunlocal.com/models/deepseek-ai-deepseek-v3/"><img src="https://doesitrunlocal.com/badge/deepseek-ai-deepseek-v3.svg" alt="Runs local: Ollama ✓ · ~487 GB" height="20"></a>

Works in GitHub READMEs and Hugging Face model cards. The badge updates when the site rebuilds.

DeepSeek-V3

Runtime status

llama.cpp

Ollama

LM Studio

MLX / mlx-lm

vLLM

Which file should I grab?

16 GB capacity estimate

24 GB capacity estimate

32 GB capacity estimate

64 GB capacity estimate

128 GB capacity estimate

192 GB capacity estimate

256 GB capacity estimate

512 GB capacity estimate

Quant uploads

Known issues

Hardware testing planned

Compare with…

Embed this badge

Get weekly local-model support updates