Mamba 2.8B HF — Hardware Requirements & GPU Compatibility
Chat
Mamba 2.8B HF is a 2.8B-parameter open language model from State Spaces. At BF16 it needs about 6.09 GB of VRAM — see which GPUs and Macs can run it below.
6.2K downloads
118 likesSpecifications
- Publisher
- State Spaces
- Parameters
- 2.8B
- Architecture
- MambaForCausalLM
- Vocabulary Size
- 50,280
- Release Date
- 2024-03-06
Get Started
HuggingFace
How Much VRAM Does Mamba 2.8B HF Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 6.1 GB | — | 5.54 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Mamba 2.8B HF?
BF16 · 6.1 GBMamba 2.8B HF (BF16) requires 6.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Mamba 2.8B HF?
BF16 · 6.1 GB33 devices with unified memory can run Mamba 2.8B HF, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Mamba 2.8B HF need?
Mamba 2.8B HF requires 6.1 GB of VRAM at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.8B × 16 bits ÷ 8 = 5.5 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
BF166.1 GB- Can I run Mamba 2.8B HF on a Mac?
Mamba 2.8B HF requires at least 6.1 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Mamba 2.8B HF locally?
Yes — Mamba 2.8B HF can run locally on consumer hardware. At BF16 quantization it needs 6.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Mamba 2.8B HF?
At BF16, Mamba 2.8B HF can reach ~479 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~108 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 6.1 × 0.55 = ~479 tok/s
Estimated speed at BF16 (6.1 GB)
~479 tok/s~108 tok/s~358 tok/s~296 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Mamba 2.8B HF?
At BF16, the download is about 5.54 GB.
- Which GPUs can run Mamba 2.8B HF?
35 consumer GPUs can run Mamba 2.8B HF at BF16 (6.1 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 28 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Mamba 2.8B HF?
33 devices with unified memory can run Mamba 2.8B HF at BF16 (6.1 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.