Cosmos Reason2 32B — Hardware Requirements & GPU Compatibility
VisionChatReasoning
Cosmos Reason 2 32B is NVIDIA's 32-billion-parameter reasoning vision-language model for physical AI and robotics, built on Qwen3-VL-32B-Instruct. Given a text prompt and an image or video, it thinks through the answer using physics understanding and common sense, and the card describes uses such as robot planning, video analytics and dataset annotation, with improved spatio-temporal understanding and timestamp precision over the first generation. At this size it needs a high-end GPU with 24 GB or more of VRAM, or a unified-memory machine, once quantized. The context window is 262,144 tokens, and the card cites input of up to 256K tokens. It is released under the NVIDIA Open Model License, which the card describes as allowing commercial use and derivative models, with additional conditions; the repository uses gated access. Published in April 2026, it sits alongside 2B and 8B siblings in the Cosmos-Reason2 family.
31.4K downloads
14 likesSpecifications
- Publisher
- NVIDIA
- Parameters
- 33.4B
- Architecture
- Qwen3VLForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-04-29
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Cosmos Reason2 32B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 14.8 GB | 57.4 GB | 14.18 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 15.2 GB | 57.8 GB | 14.59 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 16.9 GB | 59.5 GB | 16.26 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 17.3 GB | 59.9 GB | 16.68 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 20.6 GB | 63.3 GB | 20.01 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 24.4 GB | 67.0 GB | 23.77 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 28.2 GB | 70.8 GB | 27.52 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 34.0 GB | 76.6 GB | 33.36 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Cosmos Reason2 32B?
Q4_K_M · 20.6 GBCosmos Reason2 32B (Q4_K_M) requires 20.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 27+ GB is recommended. Using the full 262K context window can add up to 42.6 GB, bringing total usage to 63.3 GB. 7 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Cosmos Reason2 32B?
Q4_K_M · 20.6 GB41 devices with unified memory can run Cosmos Reason2 32B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomDecent
— Enough memory, may be tightWhere to Download Cosmos Reason2 32B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Cosmos Reason2 32B need?
Cosmos Reason2 32B requires 20.6 GB of VRAM at Q4_K_M, or 67.3 GB at BF16. Full 262K context adds up to 42.6 GB (63.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 33.4B × 4.8 bits ÷ 8 = 20 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 43.3 GB (at full 262K context)
VRAM usage by quantization
Q4_K_M20.6 GBQ4_K_M + full context63.3 GB- Can NVIDIA GeForce RTX 4090 run Cosmos Reason2 32B?
Yes, at Q5_K_S (23.6 GB) or lower. Higher quantizations like Q5_K_M (24.4 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Cosmos Reason2 32B?
For Cosmos Reason2 32B, Q4_K_M (20.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (23.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 9.8 GB.
VRAM requirement by quantization
IQ2_XXS9.8 GBIQ3_XS14.4 GBQ3_K_M16.9 GBQ4_K_M ★20.6 GBQ5_K_S23.6 GBBF1667.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Cosmos Reason2 32B on a Mac?
Cosmos Reason2 32B requires at least 9.8 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 Cosmos Reason2 32B locally?
Yes — Cosmos Reason2 32B can run locally on consumer hardware. At Q4_K_M quantization it needs 20.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Cosmos Reason2 32B?
At Q4_K_M, Cosmos Reason2 32B can reach ~232 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~32 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 20.6 × 0.65 = ~252 tok/s
Estimated speed at Q4_K_M (20.6 GB)
~252 tok/s~32 tok/s~252 tok/s~232 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Cosmos Reason2 32B?
At Q4_K_M, the download is about 20.01 GB. The full-precision BF16 version is 66.71 GB. The smallest option (IQ2_XXS) is 9.17 GB.
- Which GPUs can run Cosmos Reason2 32B?
7 consumer GPUs can run Cosmos Reason2 32B at Q4_K_M (20.6 GB). Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090. 1 GPU have plenty of headroom for comfortable inference.
- Which devices can run Cosmos Reason2 32B?
41 devices with unified memory can run Cosmos Reason2 32B at Q4_K_M (20.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.