vLLM
High-throughput LLM serving for GPUs.
Open Source 24–80 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Datacenter GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
6 GB VRAM45 tools fit this tier
AI tools that run on 6 GB VRAM
A 6 GB card is the practical floor for serious local AI in 2026. With aggressive quantization (NF4, GGUF Q4), you can run SDXL, Flux dev, and small LLMs. Long video diffusion stays out of reach — but you can absolutely learn the entire stack on this hardware.
Typical GPUs in this tier
GTX 1660 TiRTX 2060RTX 3050 / 3060 6GBRTX 4050
Capabilities
What you can run
- SDXL via Forge / A1111 with --medvram
- Flux.1 [dev] NF4 quantization
- Small LLMs (3B–7B) via Ollama / llama.cpp at Q4
- ComfyUI for image workflows (slow but functional)
- CPU-offload image upscaling
What stays out of reach
- Local video diffusion (Wan, Hunyuan, LTX)
- LoRA training above SD1.5
- EXL2 LLM quants — stick to GGUF
- Long-context (≥16k) LLMs without aggressive offload
Recommended tools for 6 GB VRAM
Sorted by best fit for this tier — tools designed around your VRAM budget first, then by our power-user score.
NVIDIA Cosmos
World-foundation models for physical AI.
Open Source 24–80 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Datacenter GPU
- Quant
- FP16
Actually FreeWatermark-FreeAPI
HunyuanVideo
13B open-weight cinematic text-to-video.
Open Source 24–48 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Workstation GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Magi-1
Autoregressive video diffusion at 24 GB.
Open Source 24–48 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Workstation GPU
- Quant
- FP8
Actually FreeNo SignupOpen SourceWatermark-Free
Mochi 1
Genmo's 10-B open-weight T2V — the first 'genuinely fluid' OSS video model.
Open Source 24–60 GB VRAM
- Min VRAM
- 24 GB
- GPU class
- Workstation GPU
- Quant
- BF16
Actually FreeNo SignupOpen SourceWatermark-Free
Modal
Serverless Python for GPU workloads.
Freemium 16–80 GB VRAM
- Min VRAM
- 16 GB
- GPU class
- Datacenter GPU
- Quant
- —
Actually FreeWatermark-FreeHobbyist-FriendlyAPI
AI-Toolkit (Ostris)
Modern training framework — Flux, SDXL, SD3 LoRAs in YAML.
Open Source 16–24 GB VRAM
- Min VRAM
- 16 GB
- GPU class
- High-end GPU
- Quant
- BF16
Actually FreeNo SignupOpen SourceWatermark-Free
TRELLIS
Microsoft Research's structured 3D representation model.
Open Source 16–24 GB VRAM
- Min VRAM
- 16 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Pyramid Flow
Memory-efficient T2V via pyramidal flow matching.
Open Source 16–24 GB VRAM
- Min VRAM
- 16 GB
- GPU class
- High-end GPU
- Quant
- BF16
Actually FreeNo SignupOpen SourceWatermark-Free
Wan 2.2
Open-weight video diffusion from Alibaba.
Open Source 12–48 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- Workstation GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Kohya_ss
The standard SDXL/Flux LoRA training UI.
Open Source 12–24 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
3D Gaussian Splatting
The INRIA original — train your own splats.
Open Source 12–24 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- Mid GPU
- Quant
- FP32
Actually FreeNo SignupWatermark-Free
Hunyuan3D-2
Tencent's open 3D generator — multi-view, PBR, ready-to-use meshes.
Open Source 12–16 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeOpen SourceWatermark-FreeAPI
LTX-Video
Real-time-ish open video diffusion from Lightricks.
Open Source 12–16 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
OneTrainer
Modern alternative trainer for SD/SDXL/Flux.
Open Source 12–24 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Stable Diffusion 3.5 Large
Stability's MMDiT flagship at 8B params.
Open Source 12–24 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeWatermark-FreeHobbyist-FriendlyAPI
SUPIR
Diffusion-based photorealistic upscaler.
Open Source 12–24 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeNo SignupWatermark-FreePlugin
CogVideoX 5B
Open-source text-to-video diffusion from THUDM.
Open Source 12–24 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
FluxGym
Dead-simple Flux LoRA training in a Gradio UI.
Open Source 12–20 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- Mid GPU
- Quant
- FP8
Actually FreeNo SignupOpen SourceWatermark-Free
Stable Video Diffusion
Image-to-video diffusion — 25 frames, 14 or 25 steps.
Open Source 12–16 GB VRAM
- Min VRAM
- 12 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeOpen SourceWatermark-FreeHobbyist-Friendly
ComfyUI-AnimateDiff-Evolved
Animation motion modules for ComfyUI.
Open Source 10–16 GB VRAM
- Min VRAM
- 10 GB
- GPU class
- High-end GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
ComfyUI
The nodal workflow engine for serious diffusion.
Open Source 6–16 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
ComfyUI ControlNet Auxiliary
All the ControlNet preprocessors in one node pack.
Open Source 6–12 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Stable Diffusion XL
The workhorse open-weight image model.
Open Source 6–12 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Text Generation WebUI
The "A1111 for LLMs" — multi-loader local chat UI.
Open Source 6–24 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- High-end GPU
- Quant
- GGUF
Actually FreeNo SignupOpen SourceWatermark-Free
Krita AI Diffusion
Stable Diffusion baked into a real painting app.
Open Source 6–12 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
TripoSR
Single-image to 3D mesh in under a second on a 4090.
Open Source 6–8 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Stable Audio Open
Open-weight text-to-audio — 47-second sound effects and music.
Open Source 6–8 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeOpen SourceWatermark-FreeHobbyist-Friendly
Stable Zero123
Novel-view synthesis — generate any angle from a single image.
Open Source 6–8 GB VRAM
- Min VRAM
- 6 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeOpen SourceWatermark-FreeHobbyist-Friendly
Diffusers
Hugging Face's go-to library for every diffusion model.
Open Source 4–12 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
AUTOMATIC1111 (stable-diffusion-webui)
The original SD power-user webUI.
Open Source 4–12 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Mid GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Topaz Video AI
GPU-accelerated upscaling, frame-interp, denoise.
Paid · from $299 4–12 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Mid GPU
- Quant
- —
Watermark-FreeHobbyist-Friendly
WhisperX
Whisper + speaker diarisation + word-level timestamps.
Open Source 4–8 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- INT8
Actually FreeOpen SourceWatermark-FreeHobbyist-Friendly
XTTS v2 (Coqui)
Multilingual voice cloning in 6 seconds.
Open Source 4–6 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Stable Diffusion WebUI Forge
Optimized A1111 fork for low-VRAM cards.
Open Source 4–8 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Flowframes
Free RIFE-based frame interpolation.
Free 4–8 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- —
Actually FreeNo SignupOpen SourceWatermark-Free
Tabby
Self-hosted, GPU-accelerated coding autocompletion.
Freemium · from $19/mo 4–8 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- GGUF
Actually FreeNo SignupOpen SourceWatermark-Free
RVC (Retrieval-based Voice Conversion)
The voice-changer that took over Discord.
Open Source 4–8 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Fooocus
Stable Diffusion XL, dialed to one button.
Open Source 4–8 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Tortoise TTS
Slow, but the quality is worth the wait.
Open Source 4–8 GB VRAM
- Min VRAM
- 4 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Transformers
The library every LLM ships against first.
Open Source 2–24 GB VRAM
- Min VRAM
- 2 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
OpenAI Whisper
The reference open-source speech-to-text model.
Open Source 2–10 GB VRAM
- Min VRAM
- 2 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
faster-whisper
Whisper, 4× faster, same accuracy. CTranslate2 backend.
Open Source 2–6 GB VRAM
- Min VRAM
- 2 GB
- GPU class
- Entry GPU
- Quant
- INT8
Actually FreeNo SignupOpen SourceWatermark-Free
FaceFusion
The most active open face-swap toolkit.
Open Source 2–8 GB VRAM
- Min VRAM
- 2 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free
Real-ESRGAN
The default OSS upscaler, still.
Open Source 2–6 GB VRAM
- Min VRAM
- 2 GB
- GPU class
- Entry GPU
- Quant
- FP16
Actually FreeNo SignupOpen SourceWatermark-Free