§01·index · /recipes
Recipes
896 community-tested setups for running open-weights AI models on real consumer GPUs.page 2 of 9
- llmintermediate16GB+
Gemma 4 12B on Apple M2 Pro: Local Private Assistant via llama.cpp / Ollama (16GB)
- llmintermediate24GB+
Gemma 4 12B on RTX 3090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate16GB+
Gemma 4 12B on RTX 4080: Local Private Assistant via llama.cpp / Ollama (16GB)
- llmintermediate12GB+
Gemma 4 12B on RTX 4070: Local Private Assistant via llama.cpp / Ollama (12GB)
- llmintermediate8GB+
Gemma 4 12B on RTX 4060: Local Private Assistant via llama.cpp / Ollama (8GB)
- llmintermediate24GB+
Gemma 4 12B on RTX 4090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate16GB+
Phi-4 (14B) on RX 7800 XT: Local Private Assistant via llama.cpp-HIP / Ollama (ROCm, 16GB)
- llmintermediate48GB+
Phi-4 (14B) on Apple M3 Max: Full-Precision Local Assistant via llama.cpp / Ollama (48GB)
- llmintermediate16GB+
Phi-4 (14B) on Apple M2 Pro: Local Private Assistant via llama.cpp / Ollama (16GB)
- llmintermediate32GB+
Phi-4 (14B) on RTX 5090: Local Private Assistant via llama.cpp / Ollama (32GB)
- llmintermediate24GB+
Phi-4 (14B) on RTX 3090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate16GB+
Phi-4 (14B) on RTX 4080: Local Private Assistant via llama.cpp / Ollama (16GB)
- llmintermediate12GB+
Phi-4 (14B) on RTX 4070: Local Private Assistant via llama.cpp / Ollama (12GB)
- llmintermediate24GB+
Phi-4 (14B) on RTX 4090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate16GB+
Mistral Nemo 12B on RX 7800 XT: Local Private Assistant via llama.cpp-HIP / Ollama (ROCm, 16GB)
- llmintermediate48GB+
Mistral Nemo 12B on Apple M3 Max (48GB): Full-Precision Local Assistant via llama.cpp / Ollama (Metal)
- llmintermediate16GB+
Mistral Nemo 12B on Apple M2 Pro (16GB): Local Private Assistant via llama.cpp / Ollama (Metal)
- llmintermediate24GB+
Mistral Nemo 12B on RTX 3090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate16GB+
Mistral Nemo 12B on RTX 4080: Local Private Assistant via llama.cpp / Ollama (16GB)
- llmintermediate12GB+
Mistral Nemo 12B on RTX 4070: Local Private Assistant via llama.cpp / Ollama (12GB)
- llmintermediate8GB+
Mistral Nemo 12B on RTX 4060: Local Private Assistant via llama.cpp / Ollama (8GB)
- llmintermediate24GB+
Mistral Nemo 12B on RTX 4090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate24GB+
Mistral Small 3.2 24B on RX 7900 XTX: Local Private Assistant via llama.cpp-HIP / Ollama (24GB ROCm)
- llmintermediate64GB+
Mistral Small 3.2 24B on M2 Max (64GB): Local Private Assistant via llama.cpp / Ollama on Apple Metal
- llmintermediate48GB+
Mistral Small 3.2 24B on M3 Max (48GB): Local Private Assistant via llama.cpp / Ollama on Apple Metal
- llmintermediate32GB+
Mistral Small 3.2 24B on RTX 5090: Local Private Assistant via llama.cpp / Ollama (32GB)
- llmintermediate24GB+
Mistral Small 3.2 24B on RTX 3090 Ti: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate24GB+
Mistral Small 3.2 24B on RTX 3090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmintermediate16GB+
Mistral Small 3.2 24B on RTX 4080: Local Private Assistant via llama.cpp / Ollama (16GB)
- llmintermediate24GB+
Mistral Small 3.2 24B on RTX 4090: Local Private Assistant via llama.cpp / Ollama (24GB)
- llmadvanced24GB+
Devstral Small 2 (24B) on RX 7900 XTX: Local Agentic Coding via llama.cpp-HIP + OpenHands (24GB ROCm)
- llmintermediate64GB+
Devstral Small 2 (24B) on Apple M2 Max: Local Agentic Coding via llama.cpp Metal + OpenHands (64GB Apple / Q8_0 default, bf16 opt-in)
- llmintermediate48GB+
Devstral Small 2 (24B) on Apple M3 Max: Local Agentic Coding via llama.cpp Metal + OpenHands (48GB Apple / Q8_0 near-lossless)
- llmintermediate32GB+
Devstral Small 2 (24B) on RTX 5090: Local Agentic Coding via llama.cpp + OpenHands (32GB Quality Tier, near-lossless Q8_0)
- llmintermediate24GB+
Devstral Small 2 (24B) on RTX 3090 Ti: Local Agentic Coding via llama.cpp + OpenHands (24GB, Faster Ampere)
- llmintermediate24GB+
Devstral Small 2 (24B) on RTX 3090: Local Agentic Coding via llama.cpp + OpenHands (24GB Value Tier)
- llmintermediate16GB+
Devstral Small 2 (24B) on RTX 4080: Local Agentic Coding via llama.cpp + OpenHands (16GB Entry Tier)
- llmadvanced24GB+
Laguna XS 2.1 on RX 7900 XTX: Local Agentic Coding via Ollama (ROCm) / llama.cpp + OpenHands (24GB Tier)
- llmadvanced24GB+
Laguna XS 2.1 on Apple M2 Max: Local Agentic Coding via Ollama + OpenHands (64GB Apple)
- llmadvanced24GB+
Laguna XS 2.1 on Apple M3 Max: Local Agentic Coding via Ollama + OpenHands (48GB Apple / q8_0-capable)
- llmadvanced24GB+
Laguna XS 2.1 on RTX 5090: Local Agentic Coding via Ollama / llama.cpp + OpenHands (32GB Tier)
- llmadvanced24GB+
Laguna XS 2.1 on RTX 3090 Ti: Local Agentic Coding via Ollama / llama.cpp + OpenHands (24GB Tier)
- llmadvanced24GB+
Laguna XS 2.1 on RTX 3090: Local Agentic Coding via Ollama / llama.cpp + OpenHands (24GB Value-Entry Tier)
- llmadvanced24GB+
North Mini Code 1.0 on RX 7900 XTX: Local Agentic Coding via llama.cpp-HIP + OpenHands (24GB ROCm Entry Tier)
- llmadvanced48GB+
North Mini Code 1.0 on Apple M2 Max: Local Agentic Coding via llama.cpp Metal + OpenHands (64GB Unified Memory)
- llmadvanced48GB+
North Mini Code 1.0 on Apple M3 Max: Local Agentic Coding via llama.cpp Metal + OpenHands (48GB Unified Memory)
- llmadvanced32GB+
North Mini Code 1.0 on RTX 5090: Local Agentic Coding via llama.cpp + OpenHands (32GB Blackwell Tier)
- llmadvanced16GB+
North Mini Code 1.0 on RTX 4080: Reduced-Quant Local Agentic Coding in 16GB via llama.cpp + OpenHands
- llmadvanced24GB+
North Mini Code 1.0 on RTX 3090 Ti: Local Agentic Coding via llama.cpp + OpenHands (24GB Entry Tier)
- llmadvanced24GB+
North Mini Code 1.0 on RTX 4090: Local Agentic Coding via llama.cpp + OpenHands (24GB Ada Tier)
- llmintermediate24GB+
Devstral Small 2 (24B) on RTX 4090: Local Agentic Coding via llama.cpp + OpenHands (24GB, the Vendor's Named Target)
- llmadvanced24GB+
Laguna XS 2.1 on RTX 4090: Local Agentic Coding via Ollama / llama.cpp + OpenHands (24GB Entry Tier)
- llmadvanced24GB+
North Mini Code 1.0 on RTX 3090: Local Agentic Coding via llama.cpp + OpenHands (24GB Entry Tier)
- llmadvanced48GB+
Ornith 1.0 35B on Apple M2 Max: Local Agentic Coding via llama.cpp Metal + OpenHands (64GB Unified Memory)
- llmadvanced48GB+
Ornith 1.0 35B on Apple M3 Max: Local Agentic Coding via llama.cpp Metal + OpenHands (48GB Unified Memory)
- llmadvanced24GB+
Ornith 1.0 35B on RX 7900 XTX: Local Agentic Coding via llama.cpp-HIP + OpenHands (24GB ROCm Entry Tier)
- llmintermediate12GB+
Ornith 1.0 9B on Apple M2 Pro: Local Agentic Coding in 16GB Unified Memory via llama.cpp Metal + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RX 7800 XT: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp-HIP + OpenHands (ROCm)
- llmintermediate12GB+
Ornith 1.0 9B on RTX 5060 Ti: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 5080: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 5070 Ti: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 4060 Ti 16GB: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 4080 SUPER: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 4070 Ti SUPER: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 4070 Ti: A Local Agentic-Coding Model in 12GB via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 4070 SUPER: A Local Agentic-Coding Model in 12GB via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 3080 Ti: A Local Agentic-Coding Model in 12GB via llama.cpp + OpenHands
- llmintermediate8GB+
Ornith 1.0 9B on RTX 5060 (8GB): Local Agentic Coding at the Fit Boundary via llama.cpp + OpenHands
- llmintermediate8GB+
Ornith 1.0 9B on RTX 4060 Ti 8GB: Local Agentic Coding at the Fit Boundary via llama.cpp + OpenHands
- llmintermediate8GB+
Ornith 1.0 9B on RTX 3060 Ti (8GB): Local Agentic Coding at the Fit Boundary via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 5070: A Local Agentic-Coding Model in 12GB via llama.cpp + OpenHands
- llmintermediate8GB+
Ornith 1.0 9B on RTX 4060 (8GB): Local Agentic Coding at the Fit Boundary via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 3060 (12GB): A Local Agentic-Coding Model on a Budget Card via llama.cpp + OpenHands
- llmintermediate12GB+
Ornith 1.0 9B on RTX 4080: Max-Fidelity Local Agentic Coding in 16GB via llama.cpp + OpenHands
- llmadvanced48GB+
Ornith 1.0 35B on Apple M4 Max: Local Agentic Coding via llama.cpp Metal + OpenHands (48GB Unified Memory)
- llmadvanced32GB+
Ornith 1.0 35B on RTX 5090: Comfortable Local Agentic Coding via llama.cpp + OpenHands (32GB Tier)
- llmadvanced24GB+
Ornith 1.0 35B on RTX 3090 Ti: Local Agentic Coding via llama.cpp + OpenHands (24GB Entry Tier)
- llmadvanced24GB+
Ornith 1.0 35B on RTX 4090: Local Agentic Coding via llama.cpp + OpenHands (24GB Entry Tier)
- llmintermediate12GB+
Ornith 1.0 9B on RTX 4070: A Local Agentic-Coding Model in 12GB via llama.cpp + OpenHands
- llmadvanced24GB+
Ornith 1.0 35B on RTX 3090: Local Agentic Coding via llama.cpp + OpenHands (24GB Entry Tier)
- multimodalintermediate24GB+
Qwen3.5-35B-A3B on RTX 5090: Blackwell MXFP4 MoE Chat at 165 tok/s
- multimodalintermediate20GB+
Qwen3.5 27B on RTX 5090: Q4_K GGUF local chat via llama.cpp
- videoadvanced14GB+
LTX-2.3 on RTX 4060 Ti 16GB: 22B Audio-Video at the 16 GB Floor via Distilled GGUF + Streamed Encoder
- llmadvanced24GB+
Llama 3.3 70B on RTX 4090: 70B-Class Chat on One 24 GB Card (Q4 Offload or Fully-On-GPU IQ2)
- llmbeginner12GB+
Qwen3-14B on RTX 4060 Ti 16GB: Q4_K_M GGUF via Ollama or llama.cpp
- llmbeginner8GB+
Llama 3.1 8B on RTX 3060 Ti: Local Chat via Ollama or llama.cpp + Unsloth UD-Q4_K_XL GGUF
- llmintermediate20GB+
Gemma 4 31B on RTX 5090: dense 31B local chat at 61 tok/s, with Q5/Q6 quality headroom in 32 GB
- videointermediate10GB+
CogVideoX 1.5 on RTX 4070 Super: 1360x768 Text-to-Video with Diffusers
- imageintermediate8GB+
Anima 2B on RTX 5060: 8GB Anime Text-to-Image via INT8 ConvRot in ComfyUI
- llmbeginner16GB+
gpt-oss 20B on RTX 5060 Ti: MXFP4 Chat at 92 tok/s via Ollama or vLLM
- llmbeginner16GB+
gpt-oss 20B on RTX 4060 Ti 16GB: MXFP4 chat at 63 tok/s via Ollama or vLLM
- imagebeginner24GB+
Flux.1 Dev on RTX 5090: ComfyUI Image Generation Guide
- imagebeginner24GB+
Flux.1 Dev on RTX 3090 Ti: ComfyUI Image Generation Guide
- llmintermediate19GB+
Qwen3-30B-A3B on RTX 5090: 226 tok/s MoE Chat with Room to Spare
- llmintermediate24GB+
Qwen3-30B-A3B on RTX 3090 Ti: 167 tok/s MoE Chat That Fits the Full 24 GB Card
- llmintermediate24GB+
Qwen3-30B-A3B on RTX 3090: Full-GPU MoE Chat at 153 tok/s
- llmadvanced32GB+
Llama 3.1 70B on RTX 5090: Fitting a 70B Model on One 32 GB Card with IQ3 GGUF
- imagebeginner4GB+
Stable Diffusion 1.5 on RTX 3060: 512x512 Image Generation with 12 GB to Spare
- llmadvanced12GB+
Qwen3.6-35B-A3B on RTX 4070: 80 tok/s + 128K context from a 12GB card via MoE CPU-offload
- llmbeginner9GB+
Qwen2.5-14B-Instruct on RX 7900 XTX: a fast local chat LLM via Ollama (ROCm)