CoolFace
15 results

gb10

inallmodelsdatasetsappsagentspeopleprojects

Models

All models matching “gb10”
ucbye /Qwen3-Coder-Next-NVFP4-GB10text-generationtransformersen4 likes407k downloads5mo agoHugging Facespele1100 /Ornith-1.5-35B-A3B-Heretic-GB10-NVFP41 likes10k downloads1mo agoHugging Facegdubicki /Qwen3-Coder-Next-NVFP4-GB10text-generationtransformersen3 likes4.9k downloads5mo agoHugging Facesaricles /Qwen3-Coder-Next-NVFP4-GB10gatedtext-generationtransformersen49 likes2.8k downloads7mo agoHugging Faceet0dev /Qwen3.5-122B-A10B-NVFP4-Full-GB10image-text-to-text1 likes1.3k downloads3mo agoHugging Faceet0dev /Qwen3.5-122B-A10B-NVFP4-FP8Dense-GB10image-text-to-text8 likes720 downloads3mo agoHugging FaceMarxistLeninist /AGILLM-GB10-1PFpytorch0 likes717 downloads1h agoHugging Facescottgl /Qwen3.5-122B-A10B-NVFP4-GB10text-generationtransformersen6 likes588 downloads5mo agoHugging Face

Datasets

All datasets matching “gb10”
mreltera /qwen3-coder-gb10-vs-rtx5090-benchmark NVIDIA GB10 vs. GeForce RTX 5090 - Local LLM Inference Benchmark Model: Qwen3-Coder-30B-A3B-InstructFormat: GGUF, Q4_K_M, 18.63 GBRuntime: LM Studio / llama.cppAuthor: Efehan A.Benchmark date: 5 August 2026 This repository contains a decode-focused local inference benchmark comparing an NVIDIA GB10 system with a Windows workstation containing two GeForce RTX 5090 GPUs. Telemetry shows that the inference workload was carried primarily by a single RTX 5090 (GPU 0), while GPU 1… See the full description on the dataset page: https://huggingface.co/datasets/mreltera/qwen3-coder-gb10-vs-rtx5090-benchmark.imagen<1K4 likes195 downloads2mo agoHugging FaceKissTheHabit /IDA-TRAIN-V2-mlperf-squad-gb10-results IDA-TRAIN-V2 MLPerf SQuAD v1.1 GB10 Results Dataset: SQuAD v1.1 — 87,599 training Q/A pairs Hardware: NVIDIA GB10 (Blackwell, sm_121a) Engine config: CUDA arch 121a, scalar_flash, legacy_bf16, optimizer lion. IDA family seats (metrics only — no weights) family arch hidden layers heads vocab phase final loss wallclock (s) micro-steps tokens seen tok/s steps/s ms/step skipped opt grad norm compute edge ida_lattice 384 8 6 32000 success 10.161242 642.088… See the full description on the dataset page: https://huggingface.co/datasets/KissTheHabit/IDA-TRAIN-V2-mlperf-squad-gb10-results.0 likes71 downloads1mo agoHugging FaceJackLiu0406 /mtl-gb10-stack0 likes18 downloads28d agoHugging Face

Apps

All apps matching “gb10”
curtburk /vLLM_on_NVIDIA_GB10static4 likes4mo agoHugging Facethetom-ai /ffai-vs-vllm-gb10gradio0 likes3mo agoHugging Facebuild-small-hackathon /ffai-vs-vllm-gb10gradio2 likes3mo agoHugging Facecurtburk /Cosmos_on_GB10static0 likes3mo agoHugging Face