§01·tested · /gpus/rx-7800-xt
Recipes tested on RX 7800 XT
46 community-tested setups — recipes whose author ran them on this exact card.
amdamd series16GB VRAM
- llmadvanced16GB+recipe
Apodex 1.1 mini on RX 7800 XT: a 36B agent in 16 GB with ROCm and llama.cpp expert offload
- multimodaladvanced16GB+recipe
Qwen3.8-27B on RX 7800 XT: a vision-capable 27B inside 16 GB on ROCm
- llmintermediate16GB+recipe
Nanbeige4.2-3B on RX 7800 XT: 96K context on a 16 GB gfx1101 ROCm build
- videoadvanced16GB+recipe
MiniMax H3 on RX 7800 XT: 16 GB video+audio in ComfyUI on ROCm (gfx1101)
- multimodaladvanced16GB+recipe
Fara1.5-9B on RX 7800 XT: a Q8_0 Browser Computer-Use Agent on ROCm gfx1101
- multimodaladvanced16GB+recipe
Fara1.5-4B on RX 7800 XT: Unquantised Browser Computer-Use Agent on ROCm gfx1101
- llmintermediate16GB+recipe
Gemma 4 12B on RX 7800 XT: Local Private Assistant via llama.cpp-HIP / Ollama (ROCm, 16GB)
- llmintermediate16GB+recipe
Phi-4 (14B) on RX 7800 XT: Local Private Assistant via llama.cpp-HIP / Ollama (ROCm, 16GB)
- llmintermediate16GB+recipe
Mistral Nemo 12B on RX 7800 XT: Local Private Assistant via llama.cpp-HIP / Ollama (ROCm, 16GB)
- llmintermediate12GB+recipe
Ornith 1.0 9B on RX 7800 XT: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp-HIP + OpenHands (ROCm)
- imageintermediate16GB+recipe
Krea 2 Turbo on RX 7800 XT via ComfyUI + ROCm: GGUF Text-to-Image in 16GB
- videoadvanced16GB+recipe
Sulphur 2 on RX 7800 XT: Uncensored LTX-2.3 Video on ROCm via ComfyUI GGUF
- 3dadvanced12GB+recipe
Waypoint 1.5 on RX 7800 XT: Real-Time Interactive World Model on ROCm (BF16)
- 3dadvanced16GB+recipe
TRELLIS image-large on RX 7800 XT: The First AMD ROCm Image-to-3D Mesh Path
- 3dadvanced10GB+recipe
Hunyuan3D-2.1 on RX 7800 XT: Image-to-Mesh on ROCm (Shape-Only)
- videoadvanced16GB+recipe
LightX2V 4-Step on RX 7800 XT: Distilled Wan2.1-T2V-14B in ComfyUI on ROCm via GGUF + 4-Step LoRA
- videoadvanced8GB+recipe
Wan 2.2 TI2V-5B on RX 7800 XT: 720p Text/Image-to-Video in ComfyUI on ROCm
- videoadvanced16GB+recipe
LTX-2.3 on RX 7800 XT: 22B Audio-Video at the 16 GB ROCm Floor via GGUF + CPU-Offloaded Gemma
- specializedintermediate3GB+recipe
KiMoDo on RX 7800 XT: Text-to-3D-Motion Generation on ROCm
- specializedbeginner4GB+recipe
SAM 3 on RX 7800 XT: Promptable Image and Video Segmentation on ROCm
- multimodalintermediate4GB+recipe
MiniMind-O on RX 7800 XT: 0.1B Omni Model on ROCm (BF16)
- multimodalbeginner6GB+recipe
Gemma 4 E4B on RX 7800 XT: Multimodal Inference via ROCm (Ollama or llama.cpp-HIP GGUF, with Q8_0)
- musicintermediate12GB+recipe
ACE-Step 1.5 XL on RX 7800 XT: Text-to-Music Generation on ROCm
- multimodalintermediate11GB+recipe
MOSS-Audio 4B-Instruct on RX 7800 XT: local audio understanding on ROCm (BF16)
- musicintermediate8GB+recipe
Foundation-1 on RX 7800 XT: Structured Music Sample Generation on ROCm
- ttsintermediate4GB+recipe
OmniVoice on RX 7800 XT: Zero-Shot Voice Cloning Across 646 Languages on ROCm (BF16)
- multimodalintermediate10GB+recipe
Voxtral Mini 3B on RX 7800 XT: local speech understanding on ROCm (~9.5 GB)
- ttsbeginner8GB+recipe
VoxCPM2 on RX 7800 XT: 30-Language 48kHz Voice Cloning on ROCm (BF16)
- ttsintermediate8GB+recipe
Qwen3-TTS 1.7B-Base on RX 7800 XT: Multilingual Voice Cloning in 10 Languages on ROCm
- ttsintermediate5GB+recipe
OpenAudio S1 Mini on RX 7800 XT: 13-Language Distilled TTS on ROCm (BF16)
- ttsbeginner5GB+recipe
VoxCPM-0.5B on RX 7800 XT: Zero-Shot Voice Cloning TTS on ROCm (BF16)
- ttsbeginner1GB+recipe
Kokoro TTS on RX 7800 XT: 82M Voice Synthesis on ROCm (BF16)
- imageintermediate9GB+recipe
ERNIE-Image-Turbo on RX 7800 XT: 8-step text-to-image via ComfyUI on ROCm (GGUF Q8_0)
- imageintermediate13GB+recipe
LongCat-Image (base T2I) on RX 7800 XT: Bilingual 6B Text-to-Image at 16 GB via ComfyUI-GGUF on ROCm
- imageintermediate14GB+recipe
HiDream-O1-Image on RX 7800 XT: 2048×2048 Text-to-Image in ComfyUI on ROCm (16 GB, Encoder-Offload)
- imageintermediate10GB+recipe
Chroma1-Base (V48) on RX 7800 XT: Uncensored 8.9B FLUX.1-Schnell De-Distillation via Q8_0 GGUF in ComfyUI on ROCm
- imageintermediate14GB+recipe
Qwen-Image on RX 7800 XT: 20B Text-to-Image via ComfyUI GGUF on ROCm (16 GB)
- imageintermediate13GB+recipe
Flux.2 Klein 4B on RX 7800 XT: ComfyUI on ROCm, BF16 4-Step Text-to-Image (16 GB)
- imageintermediate6GB+recipe
Anima 2B on RX 7800 XT: ComfyUI on ROCm (BF16/FP16)
- imageintermediate13GB+recipe
Juggernaut Z on RX 7800 XT: Cinematic Photoreal Z-Image Base Fine-Tune at BF16 via ComfyUI on ROCm
- imageintermediate13GB+recipe
Z-Image Turbo on RX 7800 XT: BF16 8-Step Text-to-Image via ComfyUI on ROCm
- imageintermediate8GB+recipe
Stable Diffusion XL on RX 7800 XT: ComfyUI on ROCm (BF16/FP16)
- llmbeginner13GB+recipe
gpt-oss 20B on RX 7800 XT: MXFP4 chat in 16 GB via Ollama or llama.cpp-HIP
- llmbeginner9GB+recipe
Qwen3-14B on RX 7800 XT: ROCm via Ollama or llama.cpp-HIP
- llmbeginner6GB+recipe
Llama 3.1 8B on Radeon RX 7800 XT: Local Chat via Ollama or llama.cpp HIP (ROCm) GGUF
- llmbeginner9GB+recipe
Qwen3-8B on RX 7800 XT: 16 GB ROCm via Ollama or llama.cpp-HIP GGUF