OpenCodeReasoning Nemotron 1.1 32B — Hardware Requirements & GPU Compatibility
ChatCodeReasoning
OpenCodeReasoning Nemotron 1.1 32B is a 32.8B-parameter open language model from NVIDIA. It supports a context window of up to 65,536 tokens. At BF16 it needs about 66.36 GB of VRAM — see which GPUs and Macs can run it below.
136 downloads
48 likesSpecifications
- Publisher
- NVIDIA
- Parameters
- 32.8B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 65,536 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2025-07-08
Get Started
HuggingFace
How Much VRAM Does OpenCodeReasoning Nemotron 1.1 32B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 66.4 GB | 83.0 GB | 65.53 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run OpenCodeReasoning Nemotron 1.1 32B?
BF16 · 66.4 GBOpenCodeReasoning Nemotron 1.1 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 66K context window can add up to 16.7 GB, bringing total usage to 83.0 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run OpenCodeReasoning Nemotron 1.1 32B?
BF16 · 66.4 GB5 devices with unified memory can run OpenCodeReasoning Nemotron 1.1 32B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Related Models
Frequently Asked Questions
- How much VRAM does OpenCodeReasoning Nemotron 1.1 32B need?
OpenCodeReasoning Nemotron 1.1 32B requires 66.4 GB of VRAM at BF16. Full 66K context adds up to 16.7 GB (83.0 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 ≈ 17.5 GB (at full 66K context)
VRAM usage by quantization
BF1666.4 GBBF16 + full context83.0 GB- Can NVIDIA GeForce RTX 5090 run OpenCodeReasoning Nemotron 1.1 32B?
No — OpenCodeReasoning Nemotron 1.1 32B requires at least 66.4 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run OpenCodeReasoning Nemotron 1.1 32B on a Mac?
OpenCodeReasoning Nemotron 1.1 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 OpenCodeReasoning Nemotron 1.1 32B locally?
Yes — OpenCodeReasoning Nemotron 1.1 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 OpenCodeReasoning Nemotron 1.1 32B?
At BF16, OpenCodeReasoning Nemotron 1.1 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 OpenCodeReasoning Nemotron 1.1 32B?
At BF16, the download is about 65.53 GB.
- Which GPUs can run OpenCodeReasoning Nemotron 1.1 32B?
No single consumer GPU has enough VRAM to run OpenCodeReasoning Nemotron 1.1 32B at BF16 (66.4 GB). Multi-GPU or professional hardware is required.
- Which devices can run OpenCodeReasoning Nemotron 1.1 32B?
5 devices with unified memory can run OpenCodeReasoning Nemotron 1.1 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.