Deepseek V3 (All Versions) - a unsloth Collection

unsloth 's Collections

DeepSeek R1 (All Versions)

Unsloth Dynamic 2.0 Quants

Qwen3

Llama 4

Phi-4 (All Versions)

Gemma 3

Unsloth 4-bit Dynamic Quants

Deepseek V3 (All Versions)

Text-to-Speech (TTS) models

Mistral Small 3 (All Versions)

Llama 3.3 (All Versions)

Qwen2.5-VL (All Versions)

Qwen QwQ-32B Collection

Vision/multimodal Models

Llama 3.2 Vision

Llama 3.1 Collection

Load 4bit models 4x faster

4bit Instruct Models

Deepseek V3 (All Versions)

updated 10 days ago

Deepseek-V3-0324 and V3 - available in original, and Dynamic GGUF formats, with support for 2-8-bit quantized versions.

unsloth/DeepSeek-V3-0324-GGUF-UD

Text Generation • Updated Apr 28 • 8.63k • 9

Note Unsloth Dynamic v2.0 GGUF:
unsloth/DeepSeek-V3-0324-GGUF

Text Generation • Updated 17 days ago • 110k • 186

Note NEW! DeepSeek-V3-0324:
unsloth/DeepSeek-V3-0324

Text Generation • Updated Apr 21 • 518 • 6
unsloth/DeepSeek-V3-0324-BF16

Text Generation • Updated Apr 19 • 649 • 2
unsloth/DeepSeek-V3-GGUF

Updated Jan 12 • 4.66k • 130

Note DeepSeek-V3:
unsloth/DeepSeek-V3-bf16

Text Generation • Updated Apr 19 • 605 • 16
unsloth/DeepSeek-V3

Text Generation • Updated Apr 30 • 88 • 13