llama.cpp-v100
llama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x V100-16GB at 262K context (6 GPUs: prefill 3402 tok/s at 200K; 2 GPUs on one socket: 2152 tok/s). Qwen3.8-27B with DFlash2 on 1-6 GPUs, up to 512K context. Multimod
Run large AI models on NVIDIA Tesla V100 GPUs for advanced tasks.
Written by the person who maintains this project, verified through the repository.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimellama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x V100-16GB at 262K context (6 GPUs: prefill 3402 tok/s at 200K; 2 GPUs on one socket: 2152 tok/s). Qwen3.8-27B with DFlash2 on 1-6 GPUs, up to 512K context. Multimod
llama.cpp-v100 has 74 stars on GitHub. It has been forked 14 times. llama.cpp-v100 is written mainly in C++. It has been in active development since 2026. llama.cpp-v100 is available under the GPL-3.0 license. Its main topics are cuda, gguf, llama-cpp, llm-inference.
What is llama.cpp-v100?
llama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x V100-16GB at 262K context (6 GPUs: prefill 3402 tok/s at 200K; 2 GPUs on one socket: 2152 tok/s). Qwen3.8-27B with DFlash2 on 1-6 GPUs, up to 512K context. Multimod
Is llama.cpp-v100 open source?
llama.cpp-v100 is an open-source project. It is released under the GPL-3.0 license.
Is llama.cpp-v100 free?
Yes. llama.cpp-v100 is free and open source — you can use, modify and self-host it. Its GPL-3.0 license is copyleft: if you distribute a modified version, it must remain under the same license.
What license does llama.cpp-v100 use?
llama.cpp-v100 is available under the GPL-3.0 license.
What language is llama.cpp-v100 written in?
llama.cpp-v100 is written mainly in C++.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/1115714829-llama-cpp-v100.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.