Cosmos Reason2 2B — Hardware Requirements & GPU Compatibility
VisionChatReasoning
Cosmos Reason2 2B is NVIDIA's 2.4-billion-parameter open reasoning vision-language model for physical AI, built on the Qwen3-VL-2B-Instruct backbone and designed to let robots and embodied agents perceive a scene and reason step by step about space, time, and physical common sense before acting. It generates long chains of thought and can output structured spatial data such as 2D/3D point localization, bounding boxes, and trajectories, plus OCR reading of scene text, going beyond a general chat assistant into physical-world planning. At just 2.4 billion parameters it is small enough to run on a single consumer GPU. Context length is 256,000 tokens, up sharply from the 16,000 tokens of the original Cosmos Reason1. It is released under the NVIDIA Open Model License, a custom license permitting commercial use and redistribution provided derivatives carry a "Built on NVIDIA Cosmos" attribution notice. It was published in December 2025, alongside a larger 8B sibling.
766.1K downloads
241 likesSpecifications
- Publisher
- NVIDIA
- Parameters
- 2.4B
- Release Date
- 2025-12-12
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Cosmos Reason2 2B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 1.1 GB | — | 1.04 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 1.3 GB | — | 1.19 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 1.6 GB | — | 1.46 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 1.9 GB | — | 1.74 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 2.2 GB | — | 2.01 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 2.7 GB | — | 2.44 GB | 8-bit quantization, near-lossless |
| BF16 | 16.00 | 5.4 GB | — | 4.88 GB | Brain floating point 16 — preferred for training |
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 Cosmos Reason2 2B?
Q4_K_M · 1.6 GBCosmos Reason2 2B (Q4_K_M) requires 1.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 3+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Cosmos Reason2 2B?
Q4_K_M · 1.6 GB59 devices with unified memory can run Cosmos Reason2 2B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Cosmos Reason2 2B
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 2B need?
Cosmos Reason2 2B requires 1.6 GB of VRAM at Q4_K_M, or 5.4 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 2.4B × 4.8 bits ÷ 8 = 1.5 GB
KV Cache + Overhead ≈ 0.1 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M1.6 GB- What's the best quantization for Cosmos Reason2 2B?
For Cosmos Reason2 2B, Q4_K_M (1.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (1.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.1 GB.
VRAM requirement by quantization
Q2_K1.1 GBQ4_K_M ★1.6 GBQ5_K_M1.9 GBQ6_K2.2 GBQ8_02.7 GBBF165.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Cosmos Reason2 2B on a Mac?
Cosmos Reason2 2B requires at least 1.1 GB at Q2_K, 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 2B locally?
Yes — Cosmos Reason2 2B can run locally on consumer hardware. At Q4_K_M quantization it needs 1.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Cosmos Reason2 2B?
At Q4_K_M, Cosmos Reason2 2B can reach ~2981 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~407 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 ÷ 1.6 × 0.65 = ~3230 tok/s
Estimated speed at Q4_K_M (1.6 GB)
~3230 tok/s~407 tok/s~3230 tok/s~2981 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 2B?
At Q4_K_M, the download is about 1.46 GB. The full-precision BF16 version is 4.88 GB. The smallest option (Q2_K) is 1.04 GB.
- Which GPUs can run Cosmos Reason2 2B?
52 consumer GPUs can run Cosmos Reason2 2B at Q4_K_M (1.6 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Cosmos Reason2 2B?
59 devices with unified memory can run Cosmos Reason2 2B at Q4_K_M (1.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, 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.