atomic.chat
@atomic_chat_hq
Run Meta's new Muse Glimmer 30B♾locally with 16GB VRAM! We ship our own GGUF quants. AD-IQ3_XXS does 62 tokens/s on a single RTX 4080 with vision and DFlash, and picks the same next token as the BF16 original 90% of the time! Run the model via Atomic Chat
X post · Local & open models· ♥ 59
ChatForm
Tgmlabs