Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

Qwen/Qwen3.8-2.4T-A95B

Text Generation • 2.4T • Updated 4 days ago • 6.38k • • 967
Qwen/Qwen3.8-2.4T-A95B-FP8

Text Generation • 2.4T • Updated 4 days ago • 10.7k • 194
Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 1 day ago • 91.9k • • 9.8k
Qwen/Qwen3.8-27B-FP8

Image-Text-to-Text • 28B • Updated 1 day ago • 123k • 427

Qwen3.8 Unsloth quants including Qwen3.8-27B! Run and train Qwen3.8 with the Unsloth Desktop app.

unsloth/Qwen3.8-27B-GGUF

27B • Updated about 19 hours ago • 868k • 1.23k
unsloth/Qwen3.8-27B-NVFP4

20B • Updated about 18 hours ago • 90.9k • 166
unsloth/Qwen3.8-2.4T-A95B-GGUF

Text Generation • 2.4T • Updated 3 days ago • 12k • 100
unsloth/Qwen3.8-27B

28B • Updated 1 day ago • 2.73k • 22

deepseek-ai/DeepSeek-V4-Flash-Base

292B • Updated Apr 27 • 388k • 294
deepseek-ai/DeepSeek-V4-Flash

Text Generation • 291B • Updated Jun 22 • 2.1M • • 2.1k
deepseek-ai/DeepSeek-V4-Pro-Base

1.6T • Updated Apr 27 • 15.7k • 328
deepseek-ai/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated Jun 22 • 1.31M • • 5.44k

Dark / Evil / NSFW Reasoning Models (gguf/source)

Models that are dark/evil/corrupt (and many times NSFW!) to begin with then I add reasoning/thinking to them to make them even... ahh... better.

DavidAU/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B

Text Generation • 8B • Updated Jul 28, 2025 • 857 • • 78
DavidAU/L3.1-Dark-Reasoning-Unholy-Hermes-R1-Uncensored-8B

Text Generation • 8B • Updated May 28, 2025 • 195 • • 22
DavidAU/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-HORROR-R1-Uncensored-36B-GGUF

Text Generation • 36B • Updated Jun 11 • 4.51k • 23
DavidAU/L3.1-Dark-Reasoning-Dark-Planet-Hermes-R1-Uncensored-Horror-Imatrix-MAX-8B-GGUF

Text Generation • 8B • Updated May 28, 2025 • 1.11k • 9

FP8 & NVFP4 quants of Qwen/Qwen3.8-27B. Reserved ahead of the upstream release — weights land as soon as the base model ships.

huginnfork/Qwen3.8-27B-FP8

Image-Text-to-Text • 28B • Updated 1 day ago • 475 • 35
huginnfork/Qwen3.8-27B-NVFP4A16

Image-Text-to-Text • 28B • Updated 1 day ago • 1.47k • 19

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter.

meta-models/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated 4 days ago • 246k • • 1.58k
meta-models/Muse-Glimmer-30B-GGUF

Image-Text-to-Text • 28B • Updated 3 days ago • 321k • 277
meta-models/Muse-Glimmer-30B-ExecuTorch-PTE

Image-Text-to-Text • Updated about 23 hours ago • 6.8k • 28
meta-models/Muse-Glimmer-30B-assistant

Image-Text-to-Text • 3B • Updated 5 days ago • 42k • 56

LTX-2.5 base models, quantized models and accompanying LoRAs and IC-LoRAs

Running on Zero

MCP

35

LTX-2.5

⚗

35

LTX-2.5 distilled two-stage
Lightricks/LTX-2.5

Image-to-Video • Updated 3 days ago • 378k • 939
Lightricks/LTX-2.5-Diffusers

Text-to-Video • 19B • Updated 4 days ago • 2.17k • 26
Lightricks/LTX-2.5-Pre-Trained

Image-to-Video • Updated 4 days ago • 573 • 24

Image NSFW editor

200+ Roleplay, Creative Writing, Uncensored, NSFW models.

Oldest models listed first, with Newest models at bottom of the page. Most repos have full examples, instructions, best settings and so on.

DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters

Updated Jul 27, 2025 • 225
DavidAU/TieFighter-Holodeck-Holomax-Mythomax-F1-V1-COMPOS-20B-gguf

Text Generation • 20B • Updated Jun 11 • 5.78k • 49
DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF-imatrix

Text Generation • 20B • Updated Jul 28, 2025 • 1.02k • 23
DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF

Text Generation • 20B • Updated Jul 28, 2025 • 836 • 25

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated 3 days ago • 2.21M • • 3.97k
Comfy-Org/MiniMax-H3

Updated 1 day ago • 12.8M • 1.34k
larryvrh/MiniMax-H3-Turbo-Lora

Text-to-Video • Updated 7 days ago • 756
drbaph/MiniMax-H3-Turbo-Lora-ComfyUI

Text-to-Video • Updated 2 days ago • 127k • 320

Qwen/Qwen3.8-2.4T-A95B

Text Generation • 2.4T • Updated 4 days ago • 6.38k • • 967
Qwen/Qwen3.8-2.4T-A95B-FP8

Text Generation • 2.4T • Updated 4 days ago • 10.7k • 194
Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 1 day ago • 91.9k • • 9.8k
Qwen/Qwen3.8-27B-FP8

Image-Text-to-Text • 28B • Updated 1 day ago • 123k • 427

Muse Glimmer 30B: multimodal agentic model for local deployment. BF16 weights, GGUF k-quants, ExecuTorch builds, DFlash drafter.

meta-models/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated 4 days ago • 246k • • 1.58k
meta-models/Muse-Glimmer-30B-GGUF

Image-Text-to-Text • 28B • Updated 3 days ago • 321k • 277
meta-models/Muse-Glimmer-30B-ExecuTorch-PTE

Image-Text-to-Text • Updated about 23 hours ago • 6.8k • 28
meta-models/Muse-Glimmer-30B-assistant

Image-Text-to-Text • 3B • Updated 5 days ago • 42k • 56

Qwen3.8 Unsloth quants including Qwen3.8-27B! Run and train Qwen3.8 with the Unsloth Desktop app.

unsloth/Qwen3.8-27B-GGUF

27B • Updated about 19 hours ago • 868k • 1.23k
unsloth/Qwen3.8-27B-NVFP4

20B • Updated about 18 hours ago • 90.9k • 166
unsloth/Qwen3.8-2.4T-A95B-GGUF

Text Generation • 2.4T • Updated 3 days ago • 12k • 100
unsloth/Qwen3.8-27B

28B • Updated 1 day ago • 2.73k • 22

LTX-2.5 base models, quantized models and accompanying LoRAs and IC-LoRAs

Running on Zero

MCP

35

LTX-2.5

⚗

35

LTX-2.5 distilled two-stage
Lightricks/LTX-2.5

Image-to-Video • Updated 3 days ago • 378k • 939
Lightricks/LTX-2.5-Diffusers

Text-to-Video • 19B • Updated 4 days ago • 2.17k • 26
Lightricks/LTX-2.5-Pre-Trained

Image-to-Video • Updated 4 days ago • 573 • 24

deepseek-ai/DeepSeek-V4-Flash-Base

292B • Updated Apr 27 • 388k • 294
deepseek-ai/DeepSeek-V4-Flash

Text Generation • 291B • Updated Jun 22 • 2.1M • • 2.1k
deepseek-ai/DeepSeek-V4-Pro-Base

1.6T • Updated Apr 27 • 15.7k • 328
deepseek-ai/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated Jun 22 • 1.31M • • 5.44k

Image NSFW editor

Dark / Evil / NSFW Reasoning Models (gguf/source)

Models that are dark/evil/corrupt (and many times NSFW!) to begin with then I add reasoning/thinking to them to make them even... ahh... better.

DavidAU/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B

Text Generation • 8B • Updated Jul 28, 2025 • 857 • • 78
DavidAU/L3.1-Dark-Reasoning-Unholy-Hermes-R1-Uncensored-8B

Text Generation • 8B • Updated May 28, 2025 • 195 • • 22
DavidAU/L3.1-MOE-6X8B-Dark-Reasoning-Dantes-Peak-HORROR-R1-Uncensored-36B-GGUF

Text Generation • 36B • Updated Jun 11 • 4.51k • 23
DavidAU/L3.1-Dark-Reasoning-Dark-Planet-Hermes-R1-Uncensored-Horror-Imatrix-MAX-8B-GGUF

Text Generation • 8B • Updated May 28, 2025 • 1.11k • 9

200+ Roleplay, Creative Writing, Uncensored, NSFW models.

Oldest models listed first, with Newest models at bottom of the page. Most repos have full examples, instructions, best settings and so on.

DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters

Updated Jul 27, 2025 • 225
DavidAU/TieFighter-Holodeck-Holomax-Mythomax-F1-V1-COMPOS-20B-gguf

Text Generation • 20B • Updated Jun 11 • 5.78k • 49
DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF-imatrix

Text Generation • 20B • Updated Jul 28, 2025 • 1.02k • 23
DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF

Text Generation • 20B • Updated Jul 28, 2025 • 836 • 25

FP8 & NVFP4 quants of Qwen/Qwen3.8-27B. Reserved ahead of the upstream release — weights land as soon as the base model ships.

huginnfork/Qwen3.8-27B-FP8

Image-Text-to-Text • 28B • Updated 1 day ago • 475 • 35
huginnfork/Qwen3.8-27B-NVFP4A16

Image-Text-to-Text • 28B • Updated 1 day ago • 1.47k • 19

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated 3 days ago • 2.21M • • 3.97k
Comfy-Org/MiniMax-H3

Updated 1 day ago • 12.8M • 1.34k
larryvrh/MiniMax-H3-Turbo-Lora

Text-to-Video • Updated 7 days ago • 756
drbaph/MiniMax-H3-Turbo-Lora-ComfyUI

Text-to-Video • Updated 2 days ago • 127k • 320

Previous
1
2
3
...
22,508
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs