meta-models

Muse Glimmer 30B

Meta's 30B multimodal model optimized for local deployment, with 4-bit K-Quant variants and a DFlash drafter for speculative decoding.image text to textapache-2.0179.1K downloadsHugging Face

Cheapest GPU in stock that fits

A single GPU with at least 64 GB for inference.

NosanaIn stock · 21 freeStart right away

1× RTX PRO 600096 GB VRAM

Nosana network, hosts worldwide

Details

Stock and price checked 16 min ago.

Self-service: you start it yourself, with no order or sales contact.

Confidential computing: data stays encrypted while the GPU works on it, so the host can't read it.

nvidia-pro-6000-cc

Full price

€2.09

per hour, whole instance, 1 GPU

View offer

GPU memory it needs

From model cards and vendor documentation. Lower precision needs less memory, with slightly lower quality. Estimates are marked.

What you want to do	Precision	Minimum	Setup	Basis
Run the model Model card target hardware for full precision. The vLLM recipe lists a 72 GB minimum for BF16.	BF16, full	64 GB	64 GB VRAM target hardware (per model card)	Published
Run the model vLLM recipe minimum for separate repo RedHatAI/Muse-Glimmer-30B-FP8-block (33 GB on disk).	FP8, 8-bit	40 GB	1 GPU, per vLLM recipe	Published
Run the model Model card target hardware for K-Quant-17GB, with 1.0% degradation versus full precision.	4-bit	24 GB	24 GB VRAM target hardware (per model card)	Published