Is VisionPsy-Nano-460M state of the art?Pending benchmarks.Announced Jul 29, 2026; no independent results yet.
A compact vision-language model from Tether's QVAC team for on-device use: it answers questions about a single image (documents, charts, diagrams, scene text) and is post-trained from Hugging Face's nanoVLM-460M-8k, which pairs a SigLIP2 vision encoder with the SmolLM2-360M language model. It comes in two variants, the accuracy-tuned VisionPsy-Nano-460M and VisionPsy-Nano-460M-Flash, which uses far fewer image tokens for faster responses on phones. Weights are on Hugging Face under Apache 2.0, with GGUF builds for llama.cpp; no API is offered.
The details so far
- Lab
- QVAC (Tether)
- Announced
- Jul 29, 2026
- API
- Not yet · None; the weights run locally
- Open weights
- Published · qvac/VisionPsy-Nano-460M and qvac/VisionPsy-Nano-460M-Flash on Hugging Face, F32 safetensors (about 2.0 GB each), loaded in Transformers with trust_remote_code; GGUF builds (FP32 to IQ3, plus a Q8 vision projector) in the -GGUFs repos for llama.cpp
- Parameters
- About 460M per QVAC (the safetensors metadata lists 507,363,296 F32 parameters for each variant)
- Type
- Vision-language model: one image plus a text prompt in, text out; English only; multi-image prompts are outside its intended use
- Architecture
- nanoVLM design: SigLIP2 base patch16-512 vision encoder, pixel-shuffle MLP connector (64 image tokens per 512x512 tile) and the SmolLM2-360M language model; images natively at 512x512, tiled up to 2048 px
- Base model
- Post-trained from lusxvr/nanoVLM-460M-8k (MIT) in five stages: generic supervised fine-tuning, capability-targeted fine-tuning, weakness-targeted fine-tuning, TIES checkpoint merging and preference alignment with replay
- Context
- 8,192 tokens
- Variants
- VisionPsy-Nano-460M (tuned for accuracy) and VisionPsy-Nano-460M-Flash (tuned for latency): same architecture and parameter count, separate checkpoints; Flash keeps each image at its native scale before tiling, so a 512x512 image takes 64 image tokens instead of 1,088
- License
- Apache 2.0 (model cards and LICENSE files); the nanoVLM base is MIT, and the card lists fine-tuning datasets under their own terms, including CC BY-NC-SA 4.0 (TabMWP) and CC BY-NC 4.0 (PKU-SafeRLHF-V)
- Developer
- Tether AI Research (Tether Data, S.A. de C.V.), published under the QVAC organization on Hugging Face and X
- Evaluation setup
- Lab-run VLMEvalKit harness with Qwen3.6-27B as the LLM judge; the VisionPsy support and scoring fixes were open VLMEvalKit pull requests at release
Tags marked unsure are not stated on the lab's own pages.
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
What the lab claims
Self-reported. Shown for context; not used in any verdict.
Lab claim: VisionPsy-Nano-460M compares favorably to LFM2.5-VL-450M, SmolVLM2-500M and nanoVLM-460M-8k on 16 of 17 benchmarks (MMVet the clear exception), with a normalized overall score of 62.3 against 59.6, 52.5 and 54.9.
Lab claim: 86.5 on ScienceQA, 42.3 on MM-IFEval and 87.9 F1 on POPE, ahead of the larger FastVLM-0.5B (759M), Qwen3.5-0.8B (873M) and InternVL3.5-1B (1061M) on those three benchmarks.
Lab claim: VisionPsy-Nano-460M-Flash reaches the first token about 19 to 23 times faster than nanoVLM-460M-8k and SmolVLM2-500M on Pixel 9, Galaxy S23 and Galaxy S25 Ultra and up to about 36 times faster on iPhone 15 (4-bit GGUF builds), and 1.3 to 2.4 times faster than LFM2.5-VL-450M.
Lab claim: Flash keeps about 99% of the full model's quality (normalized score 61.4 vs 62.3) with about 40% lower peak memory than nanoVLM-460M and SmolVLM2-500M.
Sources
LABQVAC announcement on Xx.com/qvac/status/2082439175891284476 · Jul 29, 2026LABVisionPsy-Nano (QVAC article on the Hugging Face blog)huggingface.co/blog/qvac/visionpsy · Jul 29, 2026LABQVAC post on X about VisionPsy in a robot demox.com/qvac/status/2117302716808802705 · Nov 2, 2026REPOqvac/VisionPsy-Nano-460M on Hugging Facehuggingface.co/qvac/VisionPsy-Nano-460MREPOqvac/VisionPsy-Nano-460M-Flash on Hugging Facehuggingface.co/qvac/VisionPsy-Nano-460M-FlashREPOqvac/VisionPsy-Nano-460M-GGUFs on Hugging Facehuggingface.co/qvac/VisionPsy-Nano-460M-GGUFsREPOqvac/VisionPsy-Nano-460M-Flash-GGUFs on Hugging Facehuggingface.co/qvac/VisionPsy-Nano-460M-Flash-GGUFsREPOVisionPsy collection (QVAC on Hugging Face)huggingface.co/collections/qvac/visionpsyTracking continues until an independent board lists it.