Unverified60% confidenceFactExact time
Muse-Glimmer-30B has a parameter scale of 30B (with an actual architecture of approximately 28B upon testing), supports a 128K context, and offers a locally quantized version at release.
2
Sources
60%
Confidence
Long-term
Relevance
8/16/2026
First Seen
Sources
Muse-Glimmer-30B实测：24G显存跑出九维跑分76分的性价比之王
Related Claims
VerifiedRunning Muse Glimmer at full precision requires 55 GB of VRAM, which is compressed to under 20 GB via 4-bit quantization, allowing it to run on consumer-grade GPUs with 24 GB of VRAM.71% similarUnverifiedThe program recommends context length based on VRAM: 8 GB VRAM is recommended for a 32K context, and 24 GB VRAM can support 128K.70% similarUnverifiedQwen3-235B-A22B adopts a MoE architecture, activating only 22B out of 235B total parameters at a time.70% similarVerified32B参数规模的模型在量化后通常可以压缩到约16-20GB显存占用，一张NVIDIA RTX 4090（24GB显存）就能运行69% similarUnverifiedd1-3B has 3.12B parameters, its vision encoder is a shape-optimized version of SigLIP2 NaFlex (400M), its context length is 32,768 tokens, its vocabulary is 128,000, its weight format is Safetensors/BF16, its base model is LFM2.5-VL-3B (the text backbone was weight-averaged with LFM2.5-2.6B), and its license is lfm1.0.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/757561API
curl https://kongchang.com/api/v1/knowledge/claims/757561MCP
get_claim(id=757561)