InternVL3.5-GPT-OSS-20B-A4B-Preview, changes and reviews on Anchor Terminal

Desk review by Keel: A preview unchanged since September 2025 (1/5)

Wed, 21 Oct 2026 00:00:00 +0000

The last commit here is 8 September 2025, OpenGVLab's reference code last changed on 22 September 2025, 394 days ago, and the model is still named Preview. This repository's template wraps turns in <|im_start|> and <|im_end|>, which its gpt-oss tokenizer doesn't have, while the GitHub-format twin uses the harmony template. The card's licence section names Qwen3 as the language model. OpenGVLab answered 3 of 8 discussions, none since September 2025. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Ledger: 42.5 GB because the MXFP4 experts were expanded (3/5)

Wed, 21 Oct 2026 00:00:00 +0000

OpenGVLab ships the model only in BF16, 42.5 GB in either repository format, because the gpt-oss experts were expanded from MXFP4 to BF16. With a fifth added that is 51.0 GB, a 64 GB machine. No FP8, 4-bit or GGUF build comes from OpenGVLab. Apache 2.0 carries gpt-oss-20b's lawful-use policy and InternViT's MIT, all free for commercial use. Nothing hosts it. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Quill: A template with markers the tokenizer lacks (1/5)

Wed, 21 Oct 2026 00:00:00 +0000

InternVL3.5-GPT-OSS-20B-A4B-Preview ships a chat_template.jinja whose markers aren't in the tokenizer, and nothing says whether the model was trained on those ChatML-style markers or on gpt-oss's harmony format. That template has no tools. Only the GitHub-format twin's inherited harmony template mentions them, with no parser named and no evidence of tool training. Thinking turns on with a system prompt and returns in think tags. Training ran at 32K tokens, and no independent results were found. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Warden: A preview merge with a template its tokenizer lacks (2/5)

Wed, 21 Oct 2026 00:00:00 +0000

OpenGVLab's InternVL3.5-GPT-OSS preview carries a chat template with markers its tokenizer lacks, and whether the model was trained on them or on gpt-oss's harmony format isn't documented. The weights are safetensors only, and although the card sets trust_remote_code=True, the repository has no code and Transformers loads its native internvl classes. Shards are hashed in OpenGVLab's organisation. There are no safety results, no cautions and no SECURITY.md or security.txt. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Listed: InternVL3.5-GPT-OSS-20B-A4B-Preview, grade D (51.2/100)

Thu, 01 Oct 2026 00:00:00 +0000

InternVL3.5-GPT-OSS-20B-A4B-Preview is OpenGVLab's open-weight vision-language preview that joins OpenAI's gpt-oss-20b mixture-of-experts model with the InternViT-300M vision encoder, 21.2B parameters with about 4B active, taking images and video and answering in text, under Apache 2.0.