fp8 - Robuta Search

https://huggingface.co/zai-org/GLM-4.6-FP8 zai-org/GLM-4.6-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. glm 4 6 hugging face zai fp8 https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. meta llama 4 maverick 17b 128e hugging face instruct fp8 https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1-T2V-14B_fp8_e4m3fn.safetensors Wan2_1-T2V-14B_fp8_e4m3fn.safetensors · Kijai/WanVideo_comfy at main We’re on a journey to advance and democratize artificial intelligence through open source and open science. wan2 1 t2v fp8 e4m3fn safetensors kijai wanvideo comfy 14b main https://towardsdatascience.com/breaking-the-hardware-barrier-software-fp8-for-older-gpus/ Breaking the Hardware Barrier: Software FP8 for Older GPUs | Towards Data Science Dec 29, 2025 - Deep learning workloads are increasingly memory-bound, with GPU cores sitting idle while waiting for data transfers. FP8 precision solves this on newer... towards data science breaking hardware barrier software https://huggingface.co/XLabs-AI/flux-dev-fp8/tree/main XLabs-AI/flux-dev-fp8 at main We’re on a journey to advance and democratize artificial intelligence through open source and open science. ai flux dev fp8 main https://hazyresearch.stanford.edu/blog/2024-11-27-tk-fp8 ThunderKittens: Bringing fp8 to theaters near you · Hazy Research theaters near thunderkittens bringing fp8 hazy https://huggingface.co/Qwen/Qwen3.6-27B-FP8 Qwen/Qwen3.6-27B-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 6 hugging face 27b fp8 https://huggingface.co/PrimeIntellect/INTELLECT-3-FP8 PrimeIntellect/INTELLECT-3-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. intellect 3 hugging face primeintellect fp8 https://civitai.com/models/637170/flux1-compact-or-clip-and-vae-included?modelVersionId=714945 Flux.1 Compact | CLIP and VAE included - 🟦 Flux.1-Schnell fp8 | Flux.1 Checkpoint | Civitai FLUX COMPACT I am excited to present a collection of compact Flux models, with Clips and VAE included in a single model, optimized to integrate sea... flux 1 checkpoint civitai compact clip vae https://huggingface.co/NousResearch/k2-merged-3.5T-fp8 NousResearch/k2-merged-3.5T-fp8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. 3 5t hugging face nousresearch k2 merged https://docs.vllm.ai/en/latest/api/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe/compressed_tensors_moe_w4a8_fp8/ compressed_tensors_moe_w4a8_fp8 - vLLM compressed tensors moe fp8 vllm https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/t5xxl_fp8_e4m3fn.safetensors t5xxl_fp8_e4m3fn.safetensors · comfyanonymous/flux_text_encoders at main We’re on a journey to advance and democratize artificial intelligence through open source and open science. fp8 e4m3fn safetensors text encoders flux main https://huggingface.co/zai-org/GLM-4.6V-FP8?inference_api=true&inference_provider=zai-org zai-org/GLM-4.6V-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. glm 4 6v hugging face zai fp8 https://huggingface.co/Kijai/WanVideo_comfy/blame/main/Wan2_1-I2V-14B-720P_fp8_e4m3fn.safetensors Wan2_1-I2V-14B-720P_fp8_e4m3fn.safetensors · Kijai/WanVideo_comfy at main We’re on a journey to advance and democratize artificial intelligence through open source and open science. wan2 1 i2v fp8 e4m3fn safetensors kijai wanvideo comfy 14b 720p https://hackernoon.com/how-frontier-labs-use-fp8-to-train-faster-and-spend-less How Frontier Labs Use FP8 to Train Faster and Spend Less | HackerNoon Naively casting to FP8 destroys your numerics. Here's the per-tensor and blockwise quantization mechanics that make it actually work at pretraining scale. frontier labs spend less use fp8 train https://huggingface.co/zai-org/GLM-4.6V-FP8 zai-org/GLM-4.6V-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. glm 4 6v hugging face zai fp8 https://huggingface.co/nota-ai/Solar-Open-100B-Nota-FP8 nota-ai/Solar-Open-100B-Nota-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. nota ai hugging face solar open 100b https://zencoder.ai/blog/the-reality-of-self-hosting-llms-performance-cost-and-control-with-glm-4.5-fp8-white-paper The Reality of Self-Hosting LLMs: Performance, Cost, and Control with GLM-4.5-FP8 - White paper Jan 28, 2026 - Discover which LLM is the best for coding to help you write cleaner code, fix bugs faster, and boost your productivity effortlessly. glm 4 5 self hosting performance cost white paper reality https://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-FP8 unsloth/Qwen3-VL-8B-Thinking-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen3 vl 8b hugging face unsloth thinking fp8 https://huggingface.co/unsloth/Qwen3-14B-FP8 unsloth/Qwen3-14B-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. unsloth qwen3 hugging face 14b fp8 https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8 Qwen/Qwen3.6-35B-A3B-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. qwen qwen3 6 35b a3b hugging face fp8 https://huggingface.co/zai-org/GLM-5.1-FP8?inference_api=true&inference_provider=zai-org zai-org/GLM-5.1-FP8 · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science. glm 5 1 hugging face zai fp8