DeepSeek-V3.1 VRAM & Memory Requirements

Specific checkpoints with sourced architecture and weight files. GGUF Q4_K_M (Unsloth): 378.22 GiB–444.21 GiB at 8,192 tokens, 1 sequence, FP16 KV, llama.cpp.

This result is an estimate, not a measured trace.Not verifiedFile-backed weights

Publisher and provenance

PublisherDeepSeek
Hugging Facedeepseek-ai/DeepSeek-V3.1
Revisionc0781d039fb7a1ba2abc4add0bdc293e92d2b8db
Total parameters684,531,386,000
Active parameters37,000,000,000
Layers61
Query heads128
KV heads128 (mla)
Head dimension56
Recorded context capability163,840
Completenesspartial · partial

Active parameters describe tokens' routed compute, not the full resident model weight footprint. Full-resident weight estimates use total parameters.

Memory layers in this estimate

Artifact bytes, raw KV, engine extras, and total demand are separate. This is not a runtime trace.

Weight artifact: 377.56 GiB (405,398,012,928 bytes)
Raw KV cache: 0.54 GiB (575,668,224 bytes)
Engine extras / workspace: 0.13 GiB–66.11 GiB
Total estimated demand: 378.22 GiB–444.21 GiB

Published artifacts

Quantization	Selected files	Bytes	Engine	Evidence
FP8 safetensors fp8 Calculator: FP8 safetensors	163 safetensors shards Total selected bytes: 1,369,062,772,000 (1,275.04 GiB / 1,369.06 GB) First shard: model-00001-of-000163.safetensors Last shard: model-00163-of-000163.safetensors View all 163 shard files `model-00001-of-000163.safetensors` `model-00002-of-000163.safetensors` `model-00003-of-000163.safetensors` `model-00004-of-000163.safetensors` `model-00005-of-000163.safetensors` `model-00006-of-000163.safetensors` `model-00007-of-000163.safetensors` `model-00008-of-000163.safetensors` `model-00009-of-000163.safetensors` `model-00010-of-000163.safetensors` `model-00011-of-000163.safetensors` `model-00012-of-000163.safetensors` `model-00013-of-000163.safetensors` `model-00014-of-000163.safetensors` `model-00015-of-000163.safetensors` `model-00016-of-000163.safetensors` `model-00017-of-000163.safetensors` `model-00018-of-000163.safetensors` `model-00019-of-000163.safetensors` `model-00020-of-000163.safetensors` `model-00021-of-000163.safetensors` `model-00022-of-000163.safetensors` `model-00023-of-000163.safetensors` `model-00024-of-000163.safetensors` `model-00025-of-000163.safetensors` `model-00026-of-000163.safetensors` `model-00027-of-000163.safetensors` `model-00028-of-000163.safetensors` `model-00029-of-000163.safetensors` `model-00030-of-000163.safetensors` `model-00031-of-000163.safetensors` `model-00032-of-000163.safetensors` `model-00033-of-000163.safetensors` `model-00034-of-000163.safetensors` `model-00035-of-000163.safetensors` `model-00036-of-000163.safetensors` `model-00037-of-000163.safetensors` `model-00038-of-000163.safetensors` `model-00039-of-000163.safetensors` `model-00040-of-000163.safetensors` `model-00041-of-000163.safetensors` `model-00042-of-000163.safetensors` `model-00043-of-000163.safetensors` `model-00044-of-000163.safetensors` `model-00045-of-000163.safetensors` `model-00046-of-000163.safetensors` `model-00047-of-000163.safetensors` `model-00048-of-000163.safetensors` `model-00049-of-000163.safetensors` `model-00050-of-000163.safetensors` `model-00051-of-000163.safetensors` `model-00052-of-000163.safetensors` `model-00053-of-000163.safetensors` `model-00054-of-000163.safetensors` `model-00055-of-000163.safetensors` `model-00056-of-000163.safetensors` `model-00057-of-000163.safetensors` `model-00058-of-000163.safetensors` `model-00059-of-000163.safetensors` `model-00060-of-000163.safetensors` `model-00061-of-000163.safetensors` `model-00062-of-000163.safetensors` `model-00063-of-000163.safetensors` `model-00064-of-000163.safetensors` `model-00065-of-000163.safetensors` `model-00066-of-000163.safetensors` `model-00067-of-000163.safetensors` `model-00068-of-000163.safetensors` `model-00069-of-000163.safetensors` `model-00070-of-000163.safetensors` `model-00071-of-000163.safetensors` `model-00072-of-000163.safetensors` `model-00073-of-000163.safetensors` `model-00074-of-000163.safetensors` `model-00075-of-000163.safetensors` `model-00076-of-000163.safetensors` `model-00077-of-000163.safetensors` `model-00078-of-000163.safetensors` `model-00079-of-000163.safetensors` `model-00080-of-000163.safetensors` `model-00081-of-000163.safetensors` `model-00082-of-000163.safetensors` `model-00083-of-000163.safetensors` `model-00084-of-000163.safetensors` `model-00085-of-000163.safetensors` `model-00086-of-000163.safetensors` `model-00087-of-000163.safetensors` `model-00088-of-000163.safetensors` `model-00089-of-000163.safetensors` `model-00090-of-000163.safetensors` `model-00091-of-000163.safetensors` `model-00092-of-000163.safetensors` `model-00093-of-000163.safetensors` `model-00094-of-000163.safetensors` `model-00095-of-000163.safetensors` `model-00096-of-000163.safetensors` `model-00097-of-000163.safetensors` `model-00098-of-000163.safetensors` `model-00099-of-000163.safetensors` `model-00100-of-000163.safetensors` `model-00101-of-000163.safetensors` `model-00102-of-000163.safetensors` `model-00103-of-000163.safetensors` `model-00104-of-000163.safetensors` `model-00105-of-000163.safetensors` `model-00106-of-000163.safetensors` `model-00107-of-000163.safetensors` `model-00108-of-000163.safetensors` `model-00109-of-000163.safetensors` `model-00110-of-000163.safetensors` `model-00111-of-000163.safetensors` `model-00112-of-000163.safetensors` `model-00113-of-000163.safetensors` `model-00114-of-000163.safetensors` `model-00115-of-000163.safetensors` `model-00116-of-000163.safetensors` `model-00117-of-000163.safetensors` `model-00118-of-000163.safetensors` `model-00119-of-000163.safetensors` `model-00120-of-000163.safetensors` `model-00121-of-000163.safetensors` `model-00122-of-000163.safetensors` `model-00123-of-000163.safetensors` `model-00124-of-000163.safetensors` `model-00125-of-000163.safetensors` `model-00126-of-000163.safetensors` `model-00127-of-000163.safetensors` `model-00128-of-000163.safetensors` `model-00129-of-000163.safetensors` `model-00130-of-000163.safetensors` `model-00131-of-000163.safetensors` `model-00132-of-000163.safetensors` `model-00133-of-000163.safetensors` `model-00134-of-000163.safetensors` `model-00135-of-000163.safetensors` `model-00136-of-000163.safetensors` `model-00137-of-000163.safetensors` `model-00138-of-000163.safetensors` `model-00139-of-000163.safetensors` `model-00140-of-000163.safetensors` `model-00141-of-000163.safetensors` `model-00142-of-000163.safetensors` `model-00143-of-000163.safetensors` `model-00144-of-000163.safetensors` `model-00145-of-000163.safetensors` `model-00146-of-000163.safetensors` `model-00147-of-000163.safetensors` `model-00148-of-000163.safetensors` `model-00149-of-000163.safetensors` `model-00150-of-000163.safetensors` `model-00151-of-000163.safetensors` `model-00152-of-000163.safetensors` `model-00153-of-000163.safetensors` `model-00154-of-000163.safetensors` `model-00155-of-000163.safetensors` `model-00156-of-000163.safetensors` `model-00157-of-000163.safetensors` `model-00158-of-000163.safetensors` `model-00159-of-000163.safetensors` `model-00160-of-000163.safetensors` `model-00161-of-000163.safetensors` `model-00162-of-000163.safetensors` `model-00163-of-000163.safetensors`	1,369,062,772,000 (1,275.04 GiB / 1,369.06 GB)	`vllm, sglang, unspecified`	`file-metadata`
GGUF Q4_K_M (Unsloth) gguf-q4_k_m Calculator: GGUF Q4_K_M (Unsloth)	9 safetensors shards Total selected bytes: 405,398,012,928 (377.56 GiB / 405.40 GB) First shard: Q4_K_M/DeepSeek-V3.1-Q4_K_M-00001-of-00009.gguf Last shard: Q4_K_M/DeepSeek-V3.1-Q4_K_M-00009-of-00009.gguf View all 9 shard files `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00001-of-00009.gguf` `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00002-of-00009.gguf` `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00003-of-00009.gguf` `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00004-of-00009.gguf` `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00005-of-00009.gguf` `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00006-of-00009.gguf` `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00007-of-00009.gguf` `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00008-of-00009.gguf` `Q4_K_M/DeepSeek-V3.1-Q4_K_M-00009-of-00009.gguf`	405,398,012,928 (377.56 GiB / 405.40 GB)	`llama.cpp, ollama, unspecified`	`file-metadata`
GGUF Q5_K_M (Unsloth) gguf-q5_k_m Calculator: GGUF Q5_K_M (Unsloth)	10 safetensors shards Total selected bytes: 476,161,393,760 (443.46 GiB / 476.16 GB) First shard: Q5_K_M/DeepSeek-V3.1-Q5_K_M-00001-of-00010.gguf Last shard: Q5_K_M/DeepSeek-V3.1-Q5_K_M-00010-of-00010.gguf View all 10 shard files `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00001-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00002-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00003-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00004-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00005-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00006-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00007-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00008-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00009-of-00010.gguf` `Q5_K_M/DeepSeek-V3.1-Q5_K_M-00010-of-00010.gguf`	476,161,393,760 (443.46 GiB / 476.16 GB)	`llama.cpp, ollama, unspecified`	`file-metadata`
GGUF Q6_K (Unsloth) gguf-q6_k Calculator: GGUF Q6_K (Unsloth)	12 safetensors shards Total selected bytes: 551,313,395,136 (513.45 GiB / 551.31 GB) First shard: Q6_K/DeepSeek-V3.1-Q6_K-00001-of-00012.gguf Last shard: Q6_K/DeepSeek-V3.1-Q6_K-00012-of-00012.gguf View all 12 shard files `Q6_K/DeepSeek-V3.1-Q6_K-00001-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00002-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00003-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00004-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00005-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00006-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00007-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00008-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00009-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00010-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00011-of-00012.gguf` `Q6_K/DeepSeek-V3.1-Q6_K-00012-of-00012.gguf`	551,313,395,136 (513.45 GiB / 551.31 GB)	`llama.cpp, ollama, unspecified`	`file-metadata`
GGUF Q8_0 (Unsloth) gguf-q8_0 Calculator: GGUF Q8_0 (Unsloth)	15 safetensors shards Total selected bytes: 713,286,520,224 (664.30 GiB / 713.29 GB) First shard: Q8_0/DeepSeek-V3.1-Q8_0-00001-of-00015.gguf Last shard: Q8_0/DeepSeek-V3.1-Q8_0-00015-of-00015.gguf View all 15 shard files `Q8_0/DeepSeek-V3.1-Q8_0-00001-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00002-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00003-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00004-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00005-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00006-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00007-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00008-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00009-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00010-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00011-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00012-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00013-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00014-of-00015.gguf` `Q8_0/DeepSeek-V3.1-Q8_0-00015-of-00015.gguf`	713,286,520,224 (664.30 GiB / 713.29 GB)	`llama.cpp, ollama, unspecified`	`file-metadata`
INT4 theoretical	No published file	342,265,693,000 (theoretical)	—	theoretical

Memory by quantization and context

Concurrent sequences = 1. KV defaults to FP16. The range includes documented runtime extras for the listed engine. These figures use the same core as the interactive calculator.

Quantization	2,048 tokens	8,192 tokens	32,768 tokens
FP8 safetensors	1,275.80 GiB–1,469.35 GiB	1,276.20 GiB–1,469.90 GiB	1,277.81 GiB–1,472.09 GiB
GGUF Q4_K_M (Unsloth)	377.82 GiB–443.63 GiB	378.22 GiB–444.21 GiB	379.83 GiB–446.48 GiB
GGUF Q5_K_M (Unsloth)	443.72 GiB–520.93 GiB	444.12 GiB–521.51 GiB	445.73 GiB–523.79 GiB
GGUF Q6_K (Unsloth)	513.71 GiB–603.03 GiB	514.11 GiB–603.61 GiB	515.72 GiB–605.89 GiB
GGUF Q8_0 (Unsloth)	664.56 GiB–779.98 GiB	664.96 GiB–780.56 GiB	666.57 GiB–782.83 GiB
INT4 theoretical Theoretical rows are not downloadable artifacts.	319.02 GiB–411.32 GiB	319.42 GiB–411.90 GiB	321.03 GiB–414.17 GiB

Raw KV contribution

Open the calculator with this model

Sources

DeepSeek-V3.1 model card
config.json — revision c0781d039fb7a1ba2abc4add0bdc293e92d2b8db
safetensors index — metadata.total_size=1369062772000
Artifact repo unsloth/DeepSeek-V3.1-GGUF

Assumptions that affect this result

Requested context is within the recorded native window of 163840 tokens.
Full-resident weight estimates use total parameters, including inactive MoE experts.
This MoE lists 684531386000 total parameters and 37000000000 active parameters. Active-parameter compute is not used as the weight-residency figure.
Weight bytes come from the selected weight files only, not from every file in the repository.
Download file size is not peak GPU memory. Runtime layout, allocator padding, and KV are extra.
Weight bytes come from 9 published safetensors shards totaling 405398012928 bytes.
Multi-token prediction / draft weights exist and are not included unless enabled.
Context budget is the number of cached tokens per sequence (prompt plus reserved generation).

Calculator

Loading catalog snapshot…

Choose a model first, then check a device.

Model

Show historical models

Quantization

Device type

Hardware

Workload

Context length primarily affects KV cache memory.

Advanced settings

Runtime

Engine and KV cache type for this estimate.

EngineKV cache typeRecurrent / conv state dtype Include theoretical estimates (expert) Allow a substitute if the filter has no match

Workload

Overhead scenario and the prefill workspace.

Overhead scenario Include heavier prefill workspace

Topology

How the model is split across devices. Memory is not added together.

DeploymentIntra-replica splitDevice count

Replica count is an advanced deployment option. Quantity is nodes or GPUs, not replicas.

Replica groupsDevices per replica

Budget

System reserve and safety margin. An empty number keeps the previous value.

System / display reserve

GiB (2^30 bytes)

Budget already excludes system reserveExtra safety margin

Custom bits per weightDisplay unit

Custom model

Import a config or type the architecture. Nothing is scanned until you import.

Import local config.json

Parsed in the browser. The file is not uploaded.

Public Hugging Face repoRevision

Only huggingface.co, config.json, no token. Private repos are rejected.

Total parametersActive parametersLayersQuery headsKV headsHead dimension

Search or pick a catalog checkpoint to see memory demand.

Search or pick a catalog checkpoint to see memory demand.

DeepSeek-V3.1 VRAM & Memory Requirements

Publisher and provenance

Memory layers in this estimate

Published artifacts

Memory by quantization and context

Raw KV contribution

Related pages

Sources

Assumptions that affect this result

Calculator