Cosmos Reason2 8B — Hardware Requirements & GPU Compatibility
VisionChatReasoning
Cosmos Reason2-8B is NVIDIA's 8.8-billion-parameter open reasoning vision-language model for physical AI, built on a Qwen3-VL-8B-Instruct backbone and tuned to reason step by step about video and images the way a human would when planning actions in the real world. Rather than just labeling objects, it applies physics, spatio-temporal understanding, and common sense to tasks like robot planning, autonomous-vehicle video captioning, and video-analytics annotation, producing structured outputs such as 2D/3D point localization, bounding boxes, trajectory coordinates, and on-screen OCR text. It ships alongside a smaller 2B variant for edge deployment, while the 8B model needs a capable single GPU or more, less once quantized. Context length is roughly 256,000 tokens, up sharply from 16,000 tokens in the original Cosmos Reason 1. It is released under the NVIDIA Open Model License, a custom license that permits commercial use and derivative models but requires attribution ("Built on NVIDIA Cosmos") and prohibits removing its safety guardrails. It was published in December 2025.
167.7K downloads
227 likesSpecifications
- Publisher
- NVIDIA
- Parameters
- 8.8B
- Release Date
- 2025-12-12
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Cosmos Reason2 8B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 4.1 GB | — | 3.73 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 4.2 GB | — | 3.84 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 4.7 GB | — | 4.27 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 5.8 GB | — | 5.26 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 6.9 GB | — | 6.25 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 8.0 GB | — | 7.23 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 9.6 GB | — | 8.77 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Cosmos Reason2 8B?
Q4_K_M · 5.8 GBCosmos Reason2 8B (Q4_K_M) requires 5.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 8+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3070 Ti.
Runs great
— Plenty of headroom
Decent
— Enough VRAM, may be tightWhich Devices Can Run Cosmos Reason2 8B?
Q4_K_M · 5.8 GB58 devices with unified memory can run Cosmos Reason2 8B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, MacBook Air 13" M3 (8 GB).
Runs great
— Plenty of headroomWhere to Download Cosmos Reason2 8B
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 8B need?
Cosmos Reason2 8B requires 5.8 GB of VRAM at Q4_K_M, or 19.3 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 8.8B × 4.8 bits ÷ 8 = 5.3 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M5.8 GB- What's the best quantization for Cosmos Reason2 8B?
For Cosmos Reason2 8B, Q4_K_M (5.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (6.6 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 4.1 GB.
VRAM requirement by quantization
Q2_K4.1 GBQ3_K_L4.9 GBQ4_K_M ★5.8 GBQ5_K_S6.6 GBQ5_K_M6.9 GBBF1619.3 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Cosmos Reason2 8B on a Mac?
Cosmos Reason2 8B requires at least 4.1 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 8B locally?
Yes — Cosmos Reason2 8B can run locally on consumer hardware. At Q4_K_M quantization it needs 5.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Cosmos Reason2 8B?
At Q4_K_M, Cosmos Reason2 8B can reach ~829 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~113 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 ÷ 5.8 × 0.65 = ~898 tok/s
Estimated speed at Q4_K_M (5.8 GB)
~898 tok/s~113 tok/s~898 tok/s~829 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 8B?
At Q4_K_M, the download is about 5.26 GB. The full-precision BF16 version is 17.53 GB. The smallest option (Q2_K) is 3.73 GB.
- Which GPUs can run Cosmos Reason2 8B?
52 consumer GPUs can run Cosmos Reason2 8B at Q4_K_M (5.8 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 7600. 40 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Cosmos Reason2 8B?
59 devices with unified memory can run Cosmos Reason2 8B at Q4_K_M (5.8 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.