Updated 53 min ago · first seen 11 Sept 2026
model_01M294X1EP2YKSJ8A230247FCX
- Parameters
- 8.66B
- T2 · 59 min ago
- Released
- 14 Dec 2025
- T2 · 55 min ago
- License
- apache-2.0
- T2 · 55 min ago
Specification
- Release date
- 14 Dec 2025
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Architecture
- Molmo2ForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Parameters
- 8.66B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
- Languages
- en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Base model
- Qwen/Qwen3-8B, google/siglip-so400m-patch14-384
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- File size
- 34.6 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Hugging Face repo
- allenai/Molmo2-8B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
- Downloads
- 94,605
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
- Likes
- 193
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
- Datasets
- allenai/Molmo2-Cap, allenai/Molmo2-VideoCapQA, allenai/Molmo2-VideoSubtitleQA, allenai/Molmo2-AskModelAnything, allenai/Molmo2-VideoPoint, allenai/Molmo2-VideoTrack, allenai/Molmo2-MultiImageQA, allenai/Molmo2-SynMultiImageQA, allenai/Molmo2-MultiImagePoint
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Last modified
- 2026-01-23T01:02:55+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 59 min agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Downloads all time
- 3,183,400
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 53 min agomedium
- Model type
- molmo2
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Tags
- transformers, safetensors, molmo2, image-text-to-text, multimodal, olmo, molmo, custom_code, en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
- Weights dtype
- F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
21
Source tiers
T221
Freshest observation
53 min ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
No capability flags have been observed from a source yet — we do not infer them.
- Languages
- en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 55 min agomedium
No benchmark results recorded
Current prices
No current prices recorded
Price history
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| Apple M3 Ultra | 4bit | — | 5.5 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 5.5 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 5.5 GB | Yes |
| Apple M2 Ultra | 4bit | — | 5.5 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 5.5 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 5.5 GB | Yes |
| Apple M1 Ultra | 4bit | — | 5.5 GB | Yes |
| Apple M3 Max | 4bit | — | 5.5 GB | Yes |
| Apple M4 Max | 4bit | — | 5.5 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 5.5 GB | Yes |
| Apple M2 Max | 4bit | — | 5.5 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 5.5 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 5.5 GB | Yes |
| Apple M1 Max | 4bit | — | 5.5 GB | Yes |
| Apple M4 Pro | 4bit | — | 5.5 GB | Yes |
| Apple M3 Pro | 4bit | — | 5.5 GB | Yes |
| Apple M1 Pro | 4bit | — | 5.5 GB | Yes |
| Apple M2 Pro | 4bit | — | 5.5 GB | Yes |
| Apple M4 | 4bit | — | 5.5 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 5.5 GB | Yes |
| Apple M2 | 4bit | — | 5.5 GB | Yes |
| Apple M3 | 4bit | — | 5.5 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 5.5 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 5.5 GB | Yes |
| Apple M1 | 4bit | — | 5.5 GB | Yes |
Ancestors 3
- Qwen3 8B8.19B
- siglip-so400m-patch14-384878M
- Qwen3-8B-BaseQwen
This model
Molmo2-8B
8.66B params
Quantizations 0
None recorded.
Descendants 0
None recorded.
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Datasets
Datasetsdatasets1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| allenai/Molmo2-Cap, allenai/Molmo2-VideoCapQA, allenai/Molmo2-VideoSubtitleQA, allenai/Molmo2-AskModelAnything, allenai/Molmo2-VideoPoint, allenai/Molmo2-VideoTrack, allenai/Molmo2-MultiImageQA, allenai/Molmo2-SynMultiImageQA, allenai/Molmo2-MultiImagePoint | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
New model: Molmo2-8B (Allen Institute for AI)
huggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/allenai/Molmo2-8B | model_page | T2· Quality secondary | 53 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=allenai&p=0&sort=downloads | listing | T2· Quality secondary | 56 min ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.