Molmo2 4B — Hardware Requirements & GPU Compatibility
Vision
Molmo2-4B is Allen Institute for AI's (Ai2) vision-language model for image, video, and multi-image understanding and grounding, built on a Qwen3-4B-Instruct backbone with a SigLIP 2 vision encoder. It is trained on Ai2's own curated Molmo2 datasets rather than third-party captioning data of unclear provenance, and beyond ordinary visual question answering it supports pointing at and tracking objects across video frames. The card reports state-of-the-art results among open weight-and-data models on short-video understanding, counting, and captioning, with competitive results on long videos. At under 5 billion parameters, it fits on a single consumer GPU. Context length is 36,864 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in December 2025.
105.7K downloads
54 likesSpecifications
- Publisher
- Allen AI
- Family
- OLMo
- Parameters
- 4.9B
- Architecture
- Molmo2ForConditionalGeneration
- Context Length
- 36,864 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-12-14
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Molmo2 4B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 2.5 GB | 5.8 GB | 2.06 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 2.9 GB | 6.1 GB | 2.36 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 3.4 GB | 6.6 GB | 2.91 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 3.9 GB | 7.2 GB | 3.46 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 4.5 GB | 7.7 GB | 4.00 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 5.3 GB | 8.6 GB | 4.85 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 10.2 GB | 13.4 GB | 9.70 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 Molmo2 4B?
Q4_K_M · 3.4 GBMolmo2 4B (Q4_K_M) requires 3.4 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 5+ GB is recommended. Using the full 37K context window can add up to 3.2 GB, bringing total usage to 6.6 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Molmo2 4B?
Q4_K_M · 3.4 GB59 devices with unified memory can run Molmo2 4B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, iPhone 17.
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download Molmo2 4B
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 Molmo2 4B need?
Molmo2 4B requires 3.4 GB of VRAM at Q4_K_M, or 10.2 GB at BF16. Full 37K context adds up to 3.2 GB (6.6 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 4.9B × 4.8 bits ÷ 8 = 2.9 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 3.7 GB (at full 37K context)
VRAM usage by quantization
Q4_K_M3.4 GBQ4_K_M + full context6.6 GB- What's the best quantization for Molmo2 4B?
For Molmo2 4B, Q4_K_M (3.4 GB) offers the best balance of quality and VRAM usage. Q5_K_M (3.9 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.5 GB.
VRAM requirement by quantization
Q2_K2.5 GBQ4_K_M ★3.4 GBQ5_K_M3.9 GBQ6_K4.5 GBQ8_05.3 GBBF1610.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Molmo2 4B on a Mac?
Molmo2 4B requires at least 2.5 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 Molmo2 4B locally?
Yes — Molmo2 4B can run locally on consumer hardware. At Q4_K_M quantization it needs 3.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Molmo2 4B?
At Q4_K_M, Molmo2 4B can reach ~1412 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~193 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 ÷ 3.4 × 0.65 = ~1529 tok/s
Estimated speed at Q4_K_M (3.4 GB)
~1529 tok/s~193 tok/s~1529 tok/s~1412 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Molmo2 4B?
At Q4_K_M, the download is about 2.91 GB. The full-precision BF16 version is 9.70 GB. The smallest option (Q2_K) is 2.06 GB.
- Which GPUs can run Molmo2 4B?
52 consumer GPUs can run Molmo2 4B at Q4_K_M (3.4 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 Molmo2 4B?
59 devices with unified memory can run Molmo2 4B at Q4_K_M (3.4 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.