Local LLMs & Models
74 models · benchmarks verified · VRAM calculated
Model size
VRAM required
Best for
74 models
| Name | Params | VRAM | Benchmarks | Modality | Fit |
|---|---|---|---|---|---|
| Kimi K2.6 Kimi | 1000B | - | M 87.1 C - Mth 96.4 | TextVision | |
| GLM-5.1 GLM | 744B | - | M 86 C - Mth 95.3 | Text | |
| Qwen3.6 27B Qwen · qwen3.6:27b | 28B | 16 GB | M 86.1 C 82.6 Mth 93 | TextVisionVideo | |
| DeepSeek V4 Pro DeepSeek | 1600B | - | M 90.1 C 76.8 Mth 92.6 | Text | |
| DeepSeek V4 Flash DeepSeek | 284B | - | M 88.7 C 69.5 Mth 90.8 | Text | |
| Qwen3 32B Qwen · qwen3:32b | 32B | 19 GB | M 83.4 C 82.9 Mth 94 | Text | |
| Qwen3 14B Qwen · qwen3:14b | 14B | 8 GB | M 77 C 80.5 Mth 88 | Text | |
| Phi-4 Phi · phi-4:14b | 14B | 8.5 GB | M 84.8 C 82.6 Mth 91.8 | Text | |
| Llama 3.3 70B Llama · llama3.3:70b | 70B | 40 GB | M 86 C 78.4 Mth 92.1 | Text | |
| Qwen2.5 72B Qwen · qwen2.5:72b | 72B | 40 GB | M 85 C 82 Mth 92 | Text | |
| Llama 3.1 8B Llama · llama3.1:8b | 8B | 5.5 GB | M 69.4 C 72.1 Mth 84.5 | Text | |
| Phi-4 Mini Phi · phi-4-mini:3b | 3B | 2.5 GB | M 64 C 65 Mth 78 | Text | |
| LTX 2.3 LTX | 21B | - | M - C - Mth - | VisionVideo | |
| Qwen3 ASR 1.7B Qwen | 2B | - | M - C - Mth - | AudioText | |
| Qwen3 TTS 1.7B Qwen | 2B | - | M - C - Mth - | Audio | |
| Z-Image Turbo Z-Image | 6B | - | M - C - Mth - | TextVision | |
| Wan2.1 T2V 14B Wan | 14B | - | M - C - Mth - | Video | |
| Kokoro 82M Kokoro · kokoro | 0.08B | 0.5 GB | M - C - Mth - | Audio | |
| LLaMA-Mesh LLaMA | 8B | - | M - C - Mth - | Text | |
| Whisper Large V3 Turbo Whisper | 0.8B | - | M - C - Mth - | AudioText | |
| FLUX.1 Dev FLUX | 12B | - | M - C - Mth - | TextVision | |
| Stable Audio Open 1.0 Stable Audio | 1B | - | M - C - Mth - | TextAudio | |
| Depth Anything V2 Depth Anything | 0.3B | - | M - C - Mth - | Vision | |
| Darwin-9B-NEG ansulev | 9.7B | 6 GB | M - C - Mth - | TextVision | |
| dolphin-2.9.1-yi-1.5-34b 01-ai | 34.4B | 20 GB | M - C - Mth - | Text | |
| EXAONE 4.5 33B LGAI-EXAONE | 34.4B | 20 GB | M - C - Mth - | TextVision | |
| gemma-3-1b-it | 1B | 1 GB | M - C - Mth - | Text | |
| gemma-3-270m | 0.3B | - | M - C - Mth - | Text | |
| Gemma 4 26B A4B | 26.5B | 15 GB | M - C - Mth - | TextVision | |
| Gemma 4 31B | 32.7B | 19 GB | M - C - Mth - | TextVision | |
| gpt-oss-120b openai | 120.4B | 70 GB | M - C - Mth - | Text | |
| gpt-oss-20b openai | 21.5B | 12 GB | M - C - Mth - | Text | |
| LFM2.5-1.2B-Instruct LiquidAI | 1.2B | 1 GB | M - C - Mth - | Text | |
| LLaDA-8B-Instruct GSAI-ML | 8B | 5 GB | M - C - Mth - | Text | |
| Llama-3.1-70B-Instruct meta-llama | 70.6B | 41 GB | M - C - Mth - | Text | |
| Llama-3_3-Nemotron-Super-49B-v1_5 nvidia | 49.9B | 29 GB | M - C - Mth - | Text | |
| Meta-Llama-3-8B-Instruct meta-llama | 8B | 5 GB | M - C - Mth - | Text | |
| MiMo-V2.5-Pro XiaomiMiMo | 1023.2B | 593 GB | M - C - Mth - | Text | |
| MiMo-V2.5 XiaomiMiMo | 310.8B | 180 GB | M - C - Mth - | TextVisionAudioVideo | |
| MiniMax-M2.7 MiniMaxAI | 228.7B | 133 GB | M - C - Mth - | Text | |
| Mistral-7B-Instruct-v0.2 mistralai | 7.2B | 4 GB | M - C - Mth - | Text | |
| Nemotron 3 Ultra nvidia | 253.4B | 147 GB | M - C - Mth - | Text | |
| Nemotron Cascade 2 30B A3B nvidia | 31.6B | 18 GB | M - C - Mth - | Text | |
| NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 nvidia | 31.6B | 18 GB | M - C - Mth - | Text | |
| NVIDIA Nemotron 3 Super nvidia | 67.2B | 39 GB | M - C - Mth - | Text | |
| NVIDIA-Nemotron-Nano-9B-v2 nvidia | 8.9B | 5 GB | M - C - Mth - | Text | |
| PowerMoE-3b ibm-research | 3.4B | 2 GB | M - C - Mth - | Text | |
| Qwen2-1.5B-Instruct Qwen | 1.5B | 1 GB | M - C - Mth - | Text | |
| Qwen2.5-0.5B Qwen | 0.5B | - | M - C - Mth - | Text | |
| Qwen2.5-14B-Instruct Qwen | 14.8B | 9 GB | M - C - Mth - | Text | |
| Qwen2.5-32B-Instruct Qwen | 32.8B | 19 GB | M - C - Mth - | Text | |
| Qwen2.5-Coder-14B-Instruct Qwen | 14.8B | 9 GB | M - C - Mth - | Text | |
| Qwen2.5-Coder-32B-Instruct Qwen | 32.8B | 19 GB | M - C - Mth - | Text | |
| Qwen3-30B-A3B-Instruct-2507 Qwen | 30.5B | 18 GB | M - C - Mth - | Text | |
| Qwen3-30B-A3B Qwen | 30.5B | 18 GB | M - C - Mth - | Text | |
| Qwen3-4B-Instruct-2507 Qwen | 4B | 2 GB | M - C - Mth - | Text | |
| Qwen3.5 122B A10B Qwen | 125.1B | 73 GB | M - C - Mth - | TextVision | |
| Qwen3.5 35B A3B Qwen | 36B | 21 GB | M - C - Mth - | TextVision | |
| Qwen3.5 397B A17B Qwen | 403.4B | 234 GB | M - C - Mth - | TextVision | |
| Qwen3.5 4B Qwen | 4.7B | 3 GB | M - C - Mth - | TextVision | |
| Qwen3.5 9B Qwen | 9.7B | 6 GB | M - C - Mth - | TextVision | |
| Qwen3.6 35B A3B Qwen | 36B | 21 GB | M - C - Mth - | TextVision | |
| Qwen3-Coder-30B-A3B-Instruct Qwen | 30.5B | 18 GB | M - C - Mth - | Text | |
| Qwen3-Coder-Next Qwen | 79.7B | 46 GB | M - C - Mth - | Text | |
| Qwen3-Next-80B-A3B-Instruct Qwen | 81.3B | 47 GB | M - C - Mth - | Text | |
| Rio-3.0-Open-Mini prefeitura-rio | 4B | 2 GB | M - C - Mth - | Text | |
| SmolLM2-135M HuggingFaceTB | 0.1B | - | M - C - Mth - | Text | |
| Omni Voice OmniVoice | 0.6B | - | M - C - Mth - | Audio | |
| HunyuanVideo 1.5 Hunyuan | 13B | - | M - C - Mth - | Video | |
| SAM ViT-Base SAM | 0.09B | - | M - C - Mth - | Vision | |
| YOLOv8 YOLO | 0.03B | - | M - C - Mth - | Vision | |
| MusicGen Small MusicGen | 0.6B | - | M - C - Mth - | TextAudio | |
| Stable Diffusion XL 1.0 Stable Diffusion | 3B | - | M - C - Mth - | TextVision | |
| DETR ResNet-50 DETR | 0.04B | - | M - C - Mth - | Vision |