StableBeluga2 — Hardware Requirements & GPU Compatibility
Chat
StableBeluga2 is a 70B-parameter open language model from Stability AI. It supports a context window of up to 4,096 tokens. At Q4_K_M it needs about 42.97 GB of VRAM — see which GPUs and Macs can run it below.
829 downloads
882 likesSpecifications
- Publisher
- Stability AI
- Parameters
- 70B
- Architecture
- LlamaForCausalLM
- Context Length
- 4,096 tokens
- Vocabulary Size
- 32,000
- Release Date
- 2023-07-20
Get Started
HuggingFace
How Much VRAM Does StableBeluga2 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 30.7 GB | 31.4 GB | 29.75 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 31.6 GB | 32.3 GB | 30.63 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 35.1 GB | 35.8 GB | 34.13 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 36.0 GB | 36.6 GB | 35.00 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 43.0 GB | 43.6 GB | 42.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 50.9 GB | 51.5 GB | 49.88 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 58.7 GB | 59.4 GB | 57.75 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 71.0 GB | 71.6 GB | 70.00 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run StableBeluga2?
Q4_K_M · 43.0 GBStableBeluga2 (Q4_K_M) requires 43.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 56+ GB is recommended. Using the full 4K context window can add up to 0.7 GB, bringing total usage to 43.6 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run StableBeluga2?
Q4_K_M · 43.0 GB11 devices with unified memory can run StableBeluga2, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Where to Download StableBeluga2
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does StableBeluga2 need?
StableBeluga2 requires 43.0 GB of VRAM at Q4_K_M, or 141.0 GB at BF16. Full 4K context adds up to 0.7 GB (43.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 70B × 4.8 bits ÷ 8 = 42 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.6 GB (at full 4K context)
VRAM usage by quantization
Q4_K_M43.0 GBQ4_K_M + full context43.6 GB- Can NVIDIA GeForce RTX 4090 run StableBeluga2?
Yes, at IQ2_S (22.9 GB) or lower. Higher quantizations like IQ2_M (24.6 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for StableBeluga2?
For StableBeluga2, Q4_K_M (43.0 GB) offers the best balance of quality and VRAM usage. Q5_K_S (49.1 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 20.2 GB.
VRAM requirement by quantization
IQ2_XXS20.2 GBIQ3_XS29.9 GBQ3_K_M35.1 GBQ4_K_M ★43.0 GBQ5_K_S49.1 GBBF16141.0 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run StableBeluga2 on a Mac?
StableBeluga2 requires at least 20.2 GB at IQ2_XXS, 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 StableBeluga2 locally?
Yes — StableBeluga2 can run locally on consumer hardware. At Q4_K_M quantization it needs 43.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is StableBeluga2?
At Q4_K_M, StableBeluga2 can reach ~68 tok/s on AMD Instinct MI300X. 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 ÷ 43.0 × 0.55 = ~68 tok/s
Estimated speed at Q4_K_M (43.0 GB)
~68 tok/s~51 tok/s~42 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of StableBeluga2?
At Q4_K_M, the download is about 42.00 GB. The full-precision BF16 version is 140.00 GB. The smallest option (IQ2_XXS) is 19.25 GB.
- Which GPUs can run StableBeluga2?
No single consumer GPU has enough VRAM to run StableBeluga2 at Q4_K_M (43.0 GB). Multi-GPU or professional hardware is required.
- Which devices can run StableBeluga2?
11 devices with unified memory can run StableBeluga2 at Q4_K_M (43.0 GB), including Mac Mini M4 Pro (48 GB), Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.