Pollux Judge 32B — Hardware Requirements & GPU Compatibility
Chat
Pollux Judge 32B is a 32.8B-parameter open language model from ai-forever. It supports a context window of up to 32,768 tokens. At BF16 it needs about 66.36 GB of VRAM — see which GPUs and Macs can run it below.
1.3K downloads
6 likesSpecifications
- Publisher
- ai-forever
- Parameters
- 32.8B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 151,665
- Release Date
- 2025-06-27
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Pollux Judge 32B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 66.4 GB | 74.4 GB | 65.52 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Pollux Judge 32B?
BF16 · 66.4 GBPollux Judge 32B (BF16) requires 66.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 87+ GB is recommended. Using the full 33K context window can add up to 8.0 GB, bringing total usage to 74.4 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Pollux Judge 32B?
BF16 · 66.4 GB5 devices with unified memory can run Pollux Judge 32B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Related Models
Frequently Asked Questions
- How much VRAM does Pollux Judge 32B need?
Pollux Judge 32B requires 66.4 GB of VRAM at BF16. Full 33K context adds up to 8.0 GB (74.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32.8B × 16 bits ÷ 8 = 65.5 GB
KV Cache + Overhead ≈ 0.9 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 8.9 GB (at full 33K context)
VRAM usage by quantization
BF1666.4 GBBF16 + full context74.4 GB- Can NVIDIA GeForce RTX 5090 run Pollux Judge 32B?
No — Pollux Judge 32B requires at least 66.4 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run Pollux Judge 32B on a Mac?
Pollux Judge 32B requires at least 66.4 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 Pollux Judge 32B locally?
Yes — Pollux Judge 32B can run locally on consumer hardware. At BF16 quantization it needs 66.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Pollux Judge 32B?
At BF16, Pollux Judge 32B can reach ~44 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 ÷ 66.4 × 0.55 = ~44 tok/s
Estimated speed at BF16 (66.4 GB)
~44 tok/s~33 tok/s~27 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Pollux Judge 32B?
At BF16, the download is about 65.52 GB.
- Which GPUs can run Pollux Judge 32B?
No single consumer GPU has enough VRAM to run Pollux Judge 32B at BF16 (66.4 GB). Multi-GPU or professional hardware is required.
- Which devices can run Pollux Judge 32B?
5 devices with unified memory can run Pollux Judge 32B at BF16 (66.4 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio M2 Ultra (192 GB), Mac Studio M4 Max (128 GB), NVIDIA DGX A100 640GB. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.