CMU Bamba-9B

CMU · 2025 · LLM · USA

A to Z

A · App: No
B · Built By: CMU
C · CEO & Politics: [UNKNOWN]
D · Date: 2025
E · Expertise: Intermediate+
F · Free Tier: Yes
G · Generates: Text only
H · Deployment: Cloud + Local (open weights)
I · Inputs: Text
J · Jurisdiction: USA
K · Key Staffers: Carnegie Mellon University
L · Languages: English-primary
M · Model Type: LLM
N · Safety Issues: None reported
O · Open Source: Yes — open weights
P · Pricing: Free (open weights, Apache 2.0)
Q · AIDb Rating: 5/10 · AIDb v2.0 (rule-based): Capability 4/10 · Currency 4/10 · Access 8/10 · Significance 4/10 → 4.60
R · What Makes It Special: Bamba-9B, an inference-efficient hybrid Mamba-2 language model from IBM, Princeton, CMU and UIUC, which designed the architecture together, with IBM doing most of the training: 9.78B parameters over 32 layers, trained from scratch on open data, first 2 trillion tokens of Dolma v1.7 and then 200 billion tokens of a curated high-quality blend. The team reports a 2.5x throughput gain and 2x latency speedup over standard transformers in vLLM; the weights are Apache 2.0.
S · Stock / Status: University
T · Training Cutoff: [UNKNOWN]
U · Users: [UNKNOWN]
V · Voice Chat: No
W · Weights: Downloadable
X · X Handle: @SCSatCMU
Y · Year Founded: [UNKNOWN]
Z · Bottom Line: Open-weights LLM from CMU, released 2025.

Data completeness 85% · Last verified 2026-06-11 · Primary source ↗

“CMU Bamba-9B.” AIDb — The AI Database. Verified 2026-06-11. https://theaidatabase.com/m/cmu-bamba-9b.html