Hebatron — Hardware Requirements & GPU Compatibility
Chat
Hebatron is a 31.6B-parameter open language model from HebArabNlpProject. It supports a context window of up to 262,144 tokens. At BF16 it needs about 63.53 GB of VRAM — see which GPUs and Macs can run it below.
395 downloads
17 likesSpecifications
- Publisher
- HebArabNlpProject
- Parameters
- 31.6B
- Architecture
- NemotronHForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 131,072
- Release Date
- 2026-05-13
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Hebatron Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 63.5 GB | 72.6 GB | 63.16 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Hebatron?
BF16 · 63.5 GBHebatron (BF16) requires 63.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 83+ GB is recommended. Using the full 262K context window can add up to 9.1 GB, bringing total usage to 72.6 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Hebatron?
BF16 · 63.5 GB8 devices with unified memory can run Hebatron, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightRelated Models
Frequently Asked Questions
- How much VRAM does Hebatron need?
Hebatron requires 63.5 GB of VRAM at BF16. Full 262K context adds up to 9.1 GB (72.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 31.6B × 16 bits ÷ 8 = 63.2 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 9.4 GB (at full 262K context)
VRAM usage by quantization
BF1663.5 GBBF16 + full context72.6 GB- Can NVIDIA GeForce RTX 5090 run Hebatron?
No — Hebatron requires at least 63.5 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Hebatron on a Mac?
Hebatron requires at least 63.5 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 Hebatron locally?
Yes — Hebatron can run locally on consumer hardware. At BF16 quantization it needs 63.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Hebatron?
At BF16, Hebatron can reach ~46 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 ÷ 63.5 × 0.55 = ~46 tok/s
Estimated speed at BF16 (63.5 GB)
~46 tok/s~34 tok/s~28 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Hebatron?
At BF16, the download is about 63.16 GB.
- Which GPUs can run Hebatron?
No single consumer GPU has enough VRAM to run Hebatron at BF16 (63.5 GB). Multi-GPU or professional hardware is required.
- Which devices can run Hebatron?
8 devices with unified memory can run Hebatron at BF16 (63.5 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), Mac Studio M4 Max (64 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.