Model Follower.

Up to date

Rebuilt
2026-10-25 06:54 UTC
Release radar
117 on watch
Hub snapshot
2026-10-25
Re-checked
daily · every number sourced and dated

Home › Families › deepseek-ai

DeepSeek-V4 deepseek-ai

LLMsMoE 6 members 534 derivatives on the Hub Last verified 2026-10-25 RSS

quantized: 420finetune: 101adapter: 11merge: 2

Which ones matter

Picks are rule-based from observed data (score, downloads, size, hosting); they are not quality verdicts.

Members 6

6 rows
# Model Org Role Params Band MoE License ContextProviders Price from Likes Likes 7d Downloads 30d Modified
12 DeepSeek-V4-Flash-0731 deepseek-ai Original release (shipped quantized… 304B XXL MoE MIT 1M7 $0.04 4.1k +3 4.3M 2026-08-01
17 DeepSeek-V4-Pro deepseek-ai Original release (shipped quantized… 1.60T XXL MoE MIT 1M5 $0.21 5.7k -3 361.1k 2026-06-22
28 DeepSeek-V4-Flash deepseek-ai Original release (shipped quantized… 291B XXL MoE MIT 1M4 $0.03 2.3k +12 880.3k 2026-06-22
69 DeepSeek-V4-Pro-0813 deepseek-ai Original release (shipped quantized… 1.65T XXL MoE MIT 1M6 $0.12 899 +3 151k 2026-08-13
137 DeepSeek-V4-Flash-Vision-Exp deepseek-ai Original release (shipped quantized… 305B XXL MoE MIT 1M2 $0.22 958 +4 345.8k 2026-09-01
384 DeepSeek-V4-Flash-DSpark deepseek-ai Original release (shipped quantized… 165B XXL MoE MIT 1M0 — 308 +7 148.6k 2026-07-04

Variants 150 shown of 534

Quantizations, fine-tunes, merges, and adapters of any member, ranked by downloads + likes. Filter by relation, quant family, or size band.

Relation
Quant
Size
150 rows
Variant Of Relation Quant Params Band License Author Likes Downloads
antirez/deepseek-v4-gguf deepseek-ai/DeepSeek-V4-Flash quantized gguf — — mit antirez 494 12.7M
nvidia/DeepSeek-V4-Flash-NVFP4 deepseek-ai/DeepSeek-V4-Flash quantized NVFP4 291B XXL mit nvidia 119 2M
sgl-project/DeepSeek-V4-Flash-FP8 deepseek-ai/DeepSeek-V4-Flash quantized -FP8 291B XXL mit sgl-project 15 1.8M
huihui-ai/Huihui-DeepSeek-V4-Flash-abliterated-ds4-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit huihui-ai 146 1.6M
huihui-ai/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit huihui-ai 227 1.3M
unsloth/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit unsloth 780 738.4k
MJPansa/DeepSeek-V4-Flash-0731-NVFP4 deepseek-ai/DeepSeek-V4-Flash-0731 quantized NVFP4 304B XXL mit MJPansa 18 461.6k
nvidia/DeepSeek-V4-Pro-NVFP4 deepseek-ai/DeepSeek-V4-Pro quantized NVFP4 1.60T XXL mit nvidia 81 453.6k
AtlasCloud/DeepSeek-V4-Flash-0731-FP8-DSpark deepseek-ai/DeepSeek-V4-Flash-0731 quantized -FP8 304B XXL mit AtlasCloud 5 449.1k
0xSero/deepseek-v4-flash-0731-spark deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 60.3B XL mit 0xSero 51 386.3k
nsparks/DeepSeek-V4-Flash-FP4-FP8-GGUF deepseek-ai/DeepSeek-V4-Flash quantized -FP8 — — other nsparks 16 365.3k
unsloth/DeepSeek-V4-Pro-0813-GGUF deepseek-ai/DeepSeek-V4-Pro-0813 quantized GGUF — — mit unsloth 67 296.6k
unsloth/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit unsloth 259 240.4k
bartowski/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit bartowski 36 247k
huihui-ai/Huihui-DeepSeek-V4-Flash-Vision-Exp-abliterated-GGUF deepseek-ai/DeepSeek-V4-Flash-Vision-Exp quantized GGUF — — mit huihui-ai 38 214.8k
cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit cyberneurova 62 162.5k
teamblobfish/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit teamblobfish 29 118.6k
audreyt/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit audreyt 13 114.4k
lmstudio-community/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit lmstudio-community 7 101k
sgl-project/DeepSeek-V4-Pro-FP8 deepseek-ai/DeepSeek-V4-Pro quantized -FP8 1.60T XXL mit sgl-project 13 78.5k
drowzeys/keys-DeepSeekV4-Flash-GA-0731-Dspark-Abliterated-Anchored-Tensors deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 304B XXL other drowzeys 129 71.3k
RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 deepseek-ai/DeepSeek-V4-Flash quantized NVFP4 163B XXL mit RedHatAI 25 69.8k
bartowski/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit bartowski 41 66.9k
unsloth/DeepSeek-V4-Flash deepseek-ai/DeepSeek-V4-Flash quantized — 158B XXL mit unsloth 78 63.5k
teamblobfish/DeepSeek-V4-Pro-GGUF deepseek-ai/DeepSeek-V4-Pro quantized GGUF — — mit teamblobfish 15 64.1k
tarruda/DeepSeek-V4-Flash-Vision-Exp-GGUF deepseek-ai/DeepSeek-V4-Flash-Vision-Exp quantized GGUF — — mit tarruda 2 62.7k
nvidia/DeepSeek-V4-Flash-0731-NVFP4 deepseek-ai/DeepSeek-V4-Flash-0731 quantized NVFP4 304B XXL mit nvidia 55 49k
unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF deepseek-ai/DeepSeek-V4-Flash-Vision-Exp quantized GGUF — — mit unsloth 100 44.2k
mlx-community/deepseek-ai-DeepSeek-V4-Flash-8bit deepseek-ai/DeepSeek-V4-Flash quantized -8bit 284B XXL mit mlx-community 14 46.7k
fraserprice/DeepSeek-V4-Flash-DSpark deepseek-ai/DeepSeek-V4-Flash quantized — 165B XXL mit fraserprice 9 40.7k
crusoeai/DeepSeek-V4-Flash-BF16 deepseek-ai/DeepSeek-V4-Flash finetune -BF16 284B XXL mit crusoeai 0 40.9k
ggml-org/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit ggml-org 25 38.4k
apetersson/DeepSeek-V4-Flash-0731-Abliterated-FP8 deepseek-ai/DeepSeek-V4-Flash-0731 finetune -FP8 304B XXL mit apetersson 38 37.5k
canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP deepseek-ai/DeepSeek-V4-Flash quantized -W4A16 50.7B XL mit canada-quant 20 35.4k
otheru/DeepSeek-V4-Flash-Strix-Halo-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — other otheru 27 32.8k
nazeshinjite/DeepSeek-V4-Flash-0731-ds4-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit nazeshinjite 21 32.9k
Intel/DeepSeek-V4-Flash-W4A16-AutoRound deepseek-ai/DeepSeek-V4-Flash quantized -W4A16 41.5B XL mit Intel 27 32.5k
bleysg/DeepSeek-V4-Flash-DSpark-drafter-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit bleysg 6 31k
drowzeys/DeepSeek-V4-Flash-DSpark-Abliterated-Uncensored deepseek-ai/DeepSeek-V4-Flash-DSpark quantized — 304B XXL mit drowzeys 90 25.8k
mlx-community/DeepSeek-V4-Flash deepseek-ai/DeepSeek-V4-Flash quantized — 50.6B XL mit mlx-community 3 29.9k
AtlasCloud/DeepSeek-V4-Flash-Vision-Exp-FP8-DSpark deepseek-ai/DeepSeek-V4-Flash-Vision-Exp quantized -FP8 305B XXL mit AtlasCloud 0 29.6k
qtum/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit qtum 2 29.2k
Lucebox/DeepSeek-V4-Flash-0731-ROCmFP3 deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit Lucebox 27 27.9k
AtomicChat/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit AtomicChat 32 25.9k
canada-quant/DeepSeek-V4-Flash-W4A16-FP8 deepseek-ai/DeepSeek-V4-Flash quantized -W4A16 44.1B XL mit canada-quant 16 25.1k
0xSero/DeepSeek-V4-Flash-180B deepseek-ai/DeepSeek-V4-Flash quantized — 102B XXL mit 0xSero 32 22.7k
Thump604/DeepSeek-V4-Flash-MLX-Q2-mixed-gs128-affine deepseek-ai/DeepSeek-V4-Flash quantized MLX 284B XXL mit Thump604 7 23k
nvidia/DeepSeek-V4-Flash-nvfp4-DSpark deepseek-ai/DeepSeek-V4-Flash quantized nvfp4 304B XXL mit nvidia 33 21.4k
cebeuq/DeepSeek-V4-Flash-0731-abliterated deepseek-ai/DeepSeek-V4-Flash-0731 finetune — 306B XXL mit cebeuq 44 20.4k
TensorFold/DeepSeek-V4-Flash-0731-MXFP4-MLX deepseek-ai/DeepSeek-V4-Flash-0731 quantized MXFP4 304B XXL mit TensorFold 23 21.5k
PrimeIntellect/DeepSeek-V4-Flash-0731-bf16 deepseek-ai/DeepSeek-V4-Flash-0731 finetune -bf16 284B XXL mit PrimeIntellect 0 22.6k
mlx-community/DeepSeek-V4-Pro deepseek-ai/DeepSeek-V4-Pro quantized — 267B XXL mit mlx-community 5 22.2k
Rednalreden/DeepSeek-V4-Flash-0731-dwarfstar-q2-gguf deepseek-ai/DeepSeek-V4-Flash-0731 quantized gguf — — mit Rednalreden 15 17.7k
6block/DeepSeek-V4-Pro-0813-GGUF deepseek-ai/DeepSeek-V4-Pro-0813 quantized GGUF — — mit 6block 2 18.3k
lovesenko/DeepSeek-V4-Flash-0731-Abliterated deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 304B XXL mit lovesenko 9 17.6k
mlx-community/DeepSeek-V4-Flash-0731-2.4bit-mixed deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 304B XXL mit mlx-community 28 16.2k
apetersson/DeepSeek-V4-Flash-Vision-Exp-Abliterated deepseek-ai/DeepSeek-V4-Flash-Vision-Exp finetune GGUF — — mit apetersson 18 16.5k
inferencerlabs/DeepSeek-V4-Flash-MLX-Q2i deepseek-ai/DeepSeek-V4-Flash quantized MLX — — — inferencerlabs 11 16.6k
dealignai/DeepSeek-V4-Flash-0731-JANG-CRACK deepseek-ai/DeepSeek-V4-Flash-0731 finetune — 284B XXL mit dealignai 33 15.4k
Preyazz/DeepSeek-V4-Flash-Q8_0-GGUF deepseek-ai/DeepSeek-V4-Flash quantized Q8_0 — — mit Preyazz 2 17k
mlx-community/deepseek-ai-DeepSeek-V4-Flash-4bit deepseek-ai/DeepSeek-V4-Flash quantized -4bit 284B XXL mit mlx-community 5 16.5k
MemTensor/MemT-1.0-Flash deepseek-ai/DeepSeek-V4-Flash finetune — 288B XXL mit MemTensor 77 12.5k
lovedheart/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — — lovedheart 6 15.3k
ox-ox/DeepSeek-V4-Flash-0731-gguf-ds4 deepseek-ai/DeepSeek-V4-Flash-0731 quantized gguf — — mit ox-ox 26 14.2k
audreyt/DeepSeek-V4-Flash-Vision-Exp-Abliterated-GGUF deepseek-ai/DeepSeek-V4-Flash-Vision-Exp quantized GGUF — — mit audreyt 2 14.4k
bullerwins/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — — bullerwins 6 13.9k
jedisct1/DeepSeek-V4-Flash-imatrix-aligned deepseek-ai/DeepSeek-V4-Flash quantized imatrix — — mit jedisct1 5 13.5k
apetersson/DeepSeek-V4-Flash-0731-DS4-Quality128 deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit apetersson 5 13.1k
Thump604/DeepSeek-V4-Flash-MLX-Q3-mixed-gs128-affine deepseek-ai/DeepSeek-V4-Flash quantized MLX 284B XXL mit Thump604 5 12.9k
ssweens/DeepSeek-V4-Flash-GGUF-YMMV deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit ssweens 9 12.3k
unsloth/DeepSeek-V4-Flash-0731 deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 304B XXL mit unsloth 34 11k
0xSero/DeepSeek-V4-Flash-Spark-Mini-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit 0xSero 9 12.1k
Jundot/DeepSeek-V4-Flash-0731-oQ4e-mtp deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 304B XXL mit Jundot 8 12.1k
ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF deepseek-ai/DeepSeek-V4-Flash-Vision-Exp quantized GGUF — — mit ggml-org 7 12k
KeinNiemand/DeepSeek-V4-Flash-0731-IK_GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit KeinNiemand 8 11.8k
inferencerlabs/DeepSeek-V4-Pro-MTP-MLX deepseek-ai/DeepSeek-V4-Pro quantized MLX 25.8B L — inferencerlabs 3 12k
Chunjiang-Intelligence/DeepSeek-v4-Fable deepseek-ai/DeepSeek-V4-Flash adapter — 149B XXL openrail Chunjiang-Intelligence 165 3.8k
mlx-community/DeepSeek-V4-Flash-0731-OptiQ-2bit deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 304B XXL mit mlx-community 10 11.5k
0xSero/DeepSeek-V4-Flash-0731-REAP deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 193B XXL mit 0xSero 35 8.5k
tarruda/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit tarruda 21 9.1k
bullerwins/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit bullerwins 9 9.7k
mlx-community/DeepSeek-V4-Flash-MTP-bf16 deepseek-ai/DeepSeek-V4-Flash quantized -bf16 6.61B M mit mlx-community 1 9.7k
ddh0/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — — ddh0 7 9.2k
mlx-community/deepseek-ai-DeepSeek-V4-Flash-6bit deepseek-ai/DeepSeek-V4-Flash quantized — 284B XXL mit mlx-community 2 9.3k
webbrain-one/DeepSeek-V4-Flash-0731-Vision-BF16 deepseek-ai/DeepSeek-V4-Flash-0731 quantized -BF16 305B XXL other webbrain-one 6 8.8k
mlx-community/deepseek-ai-DeepSeek-V4-Flash-3bit deepseek-ai/DeepSeek-V4-Flash quantized — 284B XXL mit mlx-community 1 8.5k
schlaflos/DeepSeek-V4-Flash-0731-antirez-ds4-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit schlaflos 10 8k
alessandrobologna/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit alessandrobologna 3 8.3k
ddalcu/DeepSeek-V4-Flash-0731-MLX-Serve-mixed-2-3-8bit deepseek-ai/DeepSeek-V4-Flash-0731 quantized MLX 324B XXL mit ddalcu 10 7.8k
orcarouter/DeepSeek-V4-Flash-Vision-Uncensored deepseek-ai/DeepSeek-V4-Flash-Vision-Exp finetune — 305B XXL mit orcarouter 71 4.8k
inferencerlabs/DeepSeek-V4-Flash-MTP-MLX deepseek-ai/DeepSeek-V4-Flash quantized MLX 6.61B M — inferencerlabs 3 7.9k
otheru/DeepSeek-V4-Flash-Vision-Strix-Halo-GGUF deepseek-ai/DeepSeek-V4-Flash-Vision-Exp quantized GGUF — — other otheru 4 7.8k
ggml-org/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit ggml-org 12 7.4k
True2456/DeepSeek-V4-Flash-0731-REAP37-native-MLX deepseek-ai/DeepSeek-V4-Flash-0731 quantized MLX 30.6B L mit True2456 15 6.9k
kshitijthakkar/deepseek-v4-mini-1B-from-flash deepseek-ai/DeepSeek-V4-Flash finetune — 1.02B S mit kshitijthakkar 10 7.1k
amd/DeepSeek-V4-Flash-MXFP4 deepseek-ai/DeepSeek-V4-Flash quantized MXFP4 149B XXL mit amd 1 7.4k
squanchyzx/DeepSeek-V4-Flash-0731-HERETIC-Abliterated-FP8 deepseek-ai/DeepSeek-V4-Flash-0731 quantized -FP8 305B XXL mit squanchyzx 21 6.4k
drowzeys/keys-DeepSeekV4Flash-Vision-EXP-ablit deepseek-ai/DeepSeek-V4-Flash-Vision-Exp finetune — 305B XXL other drowzeys 35 5.6k
0xSero/DeepSeek-V4-Flash-Spark-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit 0xSero 12 6.7k
mlx-community/DeepSeek-V4-Flash-2bit-M-DQ deepseek-ai/DeepSeek-V4-Flash quantized — 284B XXL mit mlx-community 3 6.9k
unsloth/DeepSeek-V4-Pro deepseek-ai/DeepSeek-V4-Pro quantized — 812B XXL mit unsloth 61 4k
Israeli-AI/DeepSeek-v4-flash-180b-W4A16-VOLTA-Ampere deepseek-ai/DeepSeek-V4-Flash quantized -W4A16 180B XXL mit Israeli-AI 2 6.6k
alessandrobologna/DeepSeek-V4-Flash-DSpark-Drafter-GGUF deepseek-ai/DeepSeek-V4-Flash-DSpark quantized GGUF — — mit alessandrobologna 2 6.4k
prometheusAIR/DeepSeek-V4-Flash-Vision-Exp-GGUF deepseek-ai/DeepSeek-V4-Flash-Vision-Exp quantized GGUF — — mit prometheusAIR 5 6.2k
JANGQ-AI/DeepSeek-V4-Flash-JANGTQ2 deepseek-ai/DeepSeek-V4-Flash quantized — 25.3B L mit JANGQ-AI 2 6.4k
lovesenko/DeepSeek-V4-Flash-DSpark-Abliterated deepseek-ai/DeepSeek-V4-Flash-DSpark quantized — 165B XXL mit lovesenko 9 6k
Deviad/DeepSeek-V4-Flash-MLX-Q4Q8 deepseek-ai/DeepSeek-V4-Flash quantized MLX 149B XXL mit Deviad 1 6.4k
chuzka/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit chuzka 0 6.3k
inferencerlabs/DeepSeek-V4-Flash-0731-MLX deepseek-ai/DeepSeek-V4-Flash-0731 finetune MLX — — — inferencerlabs 3 6.1k
0xSero/DeepSeek-V4-Flash-162B deepseek-ai/DeepSeek-V4-Flash quantized — 167B XXL mit 0xSero 33 4.5k
OsaurusAI/DeepSeek-V4-Flash-0731-JANG deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 284B XXL mit OsaurusAI 10 5.6k
singulared/DeepSeek-V4-Flash-0731-DSpark-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit singulared 0 6k
nvidia/DeepSeek-V4-Pro-0813-NVFP4 deepseek-ai/DeepSeek-V4-Pro-0813 quantized NVFP4 1.65T XXL mit nvidia 20 4.8k
mlx-community/DeepSeek-V4-Flash-3bit-DQ deepseek-ai/DeepSeek-V4-Flash quantized — 284B XXL mit mlx-community 2 5.7k
canada-quant/DeepSeek-V4-Flash-NVFP4-FP8-MTP deepseek-ai/DeepSeek-V4-Flash quantized NVFP4 171B XXL mit canada-quant 8 5.3k
baicai1145/DeepSeek-V4-Flash-0731-W4A16 deepseek-ai/DeepSeek-V4-Flash-0731 quantized -W4A16 44.9B XL other baicai1145 9 5.3k
YanissAmz/DeepSeek-V4-Flash-DSpark-draft-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit YanissAmz 1 5.5k
sm54/deepseek-v4-flash-0731-gguf deepseek-ai/DeepSeek-V4-Flash-0731 quantized gguf — — — sm54 4 5.3k
rogerai-fyi/DeepSeek-V4-Flash-MTP-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit rogerai-fyi 4 5.3k
Rarri/DeepSeek-V4-Flash-0731-NVFP4 deepseek-ai/DeepSeek-V4-Flash-0731 quantized NVFP4 304B XXL mit Rarri 6 5.2k
6block/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit 6block 2 5.3k
anemll/DeepSeek-V4-Flash-FP4-FP8-SSD deepseek-ai/DeepSeek-V4-Flash quantized -FP8 — — mit anemll 8 4.7k
JANGQ-AI/DeepSeek-V4-Flash-0731-JANG deepseek-ai/DeepSeek-V4-Flash-0731 quantized — 284B XXL mit JANGQ-AI 7 4.8k
Jiunsong/SuperDeepseek-V4-Flash-abliterated-MQ-2xDGX deepseek-ai/DeepSeek-V4-Flash-0731 finetune — 306B XXL mit Jiunsong 42 3k
philipjohnbasile/DeepSeek-V4-Flash-0731-MLX-M5Max-TargetOnly deepseek-ai/DeepSeek-V4-Flash-0731 finetune MLX 284B XXL mit philipjohnbasile 2 5k
tarruda/DeepSeek-V4-Flash-0731-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit tarruda 6 4.7k
thetom-ai/DeepSeek-V4-Flash-ConfigI-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit thetom-ai 6 4.7k
batiai/DeepSeek-V4-Pro-GGUF deepseek-ai/DeepSeek-V4-Pro quantized GGUF — — mit batiai 2 4.8k
amd/DeepSeek-V4-Pro-MXFP4 deepseek-ai/DeepSeek-V4-Pro quantized MXFP4 810B XXL mit amd 0 4.9k
fraserprice/DeepSeek-V4-Flash-Abliterated-DSpark deepseek-ai/DeepSeek-V4-Flash quantized — 165B XXL mit fraserprice 10 4.4k
fraserprice/DeepSeek-V4-Flash-Abliterated deepseek-ai/DeepSeek-V4-Flash quantized — 158B XXL mit fraserprice 3 4.7k
sokann/DeepSeek-V4-Flash-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit sokann 4 4.5k
puwaer/DeepSeek-V4-Flash-0731-reap-150b deepseek-ai/DeepSeek-V4-Flash-0731 finetune — 150B XXL mit puwaer 3 4.5k
lemuralabs/DeepSeek-V4-Flash-TQ-Q5.6-MLX deepseek-ai/DeepSeek-V4-Flash quantized MLX 56.0B XL mit lemuralabs 0 4.6k
sleepyeldrazi/DeepSeek-v4-Flash-REAP-K128-NVFP4 deepseek-ai/DeepSeek-V4-Flash quantized NVFP4 — — mit sleepyeldrazi 6 4.2k
Kevletesteur/DeepSeek-V4-Flash-0731-StrixHalo-Verified-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit Kevletesteur 16 3.7k
CoreWolf/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit CoreWolf 3 4.3k
dev7a/DeepSeek-V4-Flash-0731-DSpark-Drafter-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit dev7a 0 4.3k
dealignai/DeepSeek-V4-Flash-0731-CRACK-NVFP4 deepseek-ai/DeepSeek-V4-Flash-0731 finetune NVFP4 304B XXL mit dealignai 24 3k
persadian/DeepSeek-V4-Flash-IQ1_S-XL deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit persadian 3 3.9k
bullerwins/keys-DeepSeekV4-Flash-GA-0731-Dspark-Abliterated-32-32-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — other bullerwins 4 3.8k
RedHatAI/DeepSeek-V4-Flash-BF16 deepseek-ai/DeepSeek-V4-Flash finetune -BF16 284B XXL mit RedHatAI 1 3.9k
lemuralabs/DeepSeek-V4-Flash-TQ-Q4.5-MLX deepseek-ai/DeepSeek-V4-Flash quantized MLX 46.3B XL mit lemuralabs 1 3.9k
Pinaster/DeepSeek-V4-Flash-FP8-4layer deepseek-ai/DeepSeek-V4-Flash quantized -FP8 27.4B L mit Pinaster 5 3.7k
tekosML/DeepSeek-V4-Flash-0731-GGUF-GX10 deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit tekosML 2 3.8k
amd/DeepSeek-V4-Flash-EXTENSOR deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — mit amd 2 3.6k
lemuralabs/DeepSeek-V4-Flash-TQ-Q2.3-MLX deepseek-ai/DeepSeek-V4-Flash quantized MLX 27.3B L mit lemuralabs 0 3.6k
andreaborio/DeepSeek-V4-Flash-Hebrus-GGUF deepseek-ai/DeepSeek-V4-Flash quantized GGUF — — mit andreaborio 2 3.4k
kingjones777/DeepSeek-V4-Flash-180B-ROCmFP4-STRIX_LEAN-GGUF deepseek-ai/DeepSeek-V4-Flash-0731 quantized GGUF — — apache-2.0 kingjones777 6 3.2k
qtum/DeepSeek-V4-Pro-0813-GGUF deepseek-ai/DeepSeek-V4-Pro-0813 quantized GGUF — — mit qtum 1 3.4k

Get alerts on the DeepSeek-V4 family

Watch this family

Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.