OrionLLM/GRM2-3b-GGUF
4B • Updated • 6.09k • 5
André Leo Bjørningstad
LeoHyperlink
AI & ML interests
None yet
Recent Activity
liked a model about 11 hours ago
OrionLLM/GRM2-3b-GGUF liked a model about 15 hours ago
Hcompany/Holo3-35B-A3B liked a model about 15 hours ago
mradermacher/Holo3-35B-A3B-GGUFOrganizations
liked a
model about 11 hours ago
liked 2
models about 15 hours ago
liked 6
models 19 days ago
unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF
Text Generation • 121B • Updated • 94.1k • 103
LocoreMind/LocoTrainer-4B
Text Generation • 4B • Updated • 2.1k • 55
Tesslate/OmniCoder-9B
Text Generation • Updated • 31.6k • 562
janhq/Jan-code-4b-gguf
Text Generation • 4B • Updated • 26.4k • 58
janhq/Qwen3.5-35B-A3B-GGUF
Image-Text-to-Text • 35B • Updated • 13.7k • 5
janhq/Jan-v2-VL-max-gguf
Image-Text-to-Text • 31B • Updated • 6.61k • 4
liked 4
models about 1 month ago
upvoted an article about 1 month ago
Article
GGML and llama.cpp join HF to ensure the long-term progress of Local AI
- +4
•
492
liked a
model about 2 months ago
reactedto danielhanchen's post with 🔥 about 2 months ago
Post
5209
We collaborated with Hugging Face to enable you to train MoE models 12× faster with 35% less VRAM via our new Triton kernels (no accuracy loss). 🤗
Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe
Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe
- 1 reply
liked 2
models about 2 months ago
repliedto danielhanchen's post about 2 months ago
I got qwen3-coder-next up 24tps when i removed -nkvo and kept -kvu. Think i could increase it further if i took the time to compile llama.cpp and not use docker image.
upvoted a collection about 2 months ago