FitMyLLM
IBM/Dense

IBMBamba 9B v2

We introduce Bamba-9B-v2, a decoder-only language model based on the Mamba-2 architecture and is designed to handle a wide range of text generation tasks. Bamba v2 is trained for an additional 1T tokens that significantly improves on Bamba v1.

chat
9.78B
Parameters
256K
Context length
6
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2025-04-29
Layers
32
KV Heads
8
Head Dim
128
Family
other

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
8.0 GB
6.5 + 1.5 KV
good
Q5_K_S5.57
8.8 GB
7.3 + 1.5 KV
good
Q5_K_M5.7
9.0 GB
7.5 + 1.5 KV
good
Q6_K6.56
10.0 GB
8.5 + 1.5 KV
excellent
Q8_08.5
12.4 GB
10.9 + 1.5 KV
lossless
FP1616
21.5 GB
20.0 + 1.5 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run Bamba 9B v2 now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (6)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$# Bamba 9B v2 is not in Ollama's library, and we know no GGUF build of it

Search Hugging Face for a GGUF of it (https://huggingface.co/models?sort=trending&search=Bamba-9B-v2+GGUF), or use the vLLM tab with the original weights.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Apple M1 (8GB)
8 GB VRAM • 68 GB/s
APPLE
$499
Apple M2 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
Apple M3 (8GB)
8 GB VRAM • 100 GB/s
APPLE
$599
NVIDIA Tesla K8
8 GB VRAM • 160 GB/s
NVIDIA
NVIDIA Tesla M60
8 GB VRAM • 160 GB/s
NVIDIA

Find the best GPU for Bamba 9B v2

Build Hardware for Bamba 9B v2
Spec sheet

Bamba 9B v2 — 9.78B Dense.

Specifications
Parameters
9.78B
Architecture
Dense Transformer
Context Length
256K tokens
Capabilities
chat
Release Date
2025-04-29
Provider
IBM
Family
other
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.896.5 GB94%
Q5_K_S5.577.3 GB96%
Q5_K_M5.77.5 GB96%
Q6_K6.568.5 GB97%
Q8_08.510.9 GB100%
FP161620.0 GB100%
Benchmark scores
MMLU-PRO28.8
MATH15.2
IFEval68.6
BBH31.9
GPQA5.3
MUSR6.6
Compatible GPUs
30 @ Q4_K_M