The story so far
Weights, every dated article, and repo commits on one rail.
4 repo commits since the weights landed
Teal is the weights (2026-09-26), grey ticks are repo commits.
Intern-Decision-2B
internlm Apache 2.0 out 29 days ago
2.21B parameters, images and text in, text out, 256K tokens of context.
Verified 2026-10-25 Rank #4514 in Decision models · score 50.3 method v1 Sources 3 Downloads 30d 2.6k · #574 of 619 tracked
Do people use it?2.6kdownloads, 30 days#574 of 619 we track · below the median+0 likes, downloads +22% this week18 likesHugging Face2026-10-24
Where it's used
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 2 quantized builds and 6 Spaces.
- As a service0no API provider listed
- On own hardware2quantized builds
- Built on00 fine-tunes · 0 adapters · 0 merges
- In apps6Hugging Face Spaces
Top Spaces running it: multimodalart/jev-decision-index ♥ 802
Will it fit?
Weights only, an estimate: leave room for the KV cache. Method
Fits a 16 GB card at INT4
About 1.3 GB at INT4, 2.7 GB at FP8, 5.3 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
What people built on it
2 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
2 derivatives on the Hub, most of them quantized
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Reference
Everything else, folded: the full tables, every source.
Benchmarks
10 rows
Benchmarks 10 rows
measured third-party leaderboard rowauthor-reported number from the model card or eval files (10)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported AG News | 89.96 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported Average | 84.68 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported Brier ↓ | 0.44 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported ECE ↓ | 0.1 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported Jevbench-Easy | 100 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported Jevbench-Hard | 63.96 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported Jevbench-Original | 84.72 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported ToolACE | 96.45 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported Typed Decision | 79.35 | Intern-Decision-2B | model author | 2026-10-23 |
| author-reported WildJailBreak | 78.33 | Intern-Decision-2B | model author | 2026-10-23 |
What the card says
2 cited sentences
Summary generated, cited
Intern-Decision-2B is a 2.21B parameter multimodal structured decision model fine-tuned from Qwen/Qwen3.5-2B.[1][2] The model uses a Qwen3_5ForConditionalGeneration architecture to return an answer distribution for questions in one forward pass.[3][4]
- parameters human
- “fine-tuned from Qwen3.5-2B”
- architectures
- “returns an answer distribution for every question in one …”
Generated 2026-10-07 15:17 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Use-case evidence
7 use cases
What it is good at 7 use cases
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
- Understand images and videostructuraldecision-model estimate p=0.75tag: multimodalpipeline: image-text-to-text+1 more
- Classify and make typed decisionsstructuraldecision-model estimate p=1.00name: Decisiondecision catalog
- Run on a laptop or phonestructuraldecision-model estimate p=0.96name: 2Bfits: single-gpu
- Chat and follow instructionsstructuraltag: conversationalchat template present
- Call tools and APIsstructuralchat template: <tool_call>
- Reason through hard problemsstructuralchat template: <think>
- Read long documentsstructuralconfig: 262,144 context
Facts
20 fields
Listed in Decision models · LLMs
Facts
- Intern-Decision-2B has 2.21B parameters. (safetensors metadata, observed 2026-10-24)
- Context length is 262,144 tokens (256K). (config.json max_position_embeddings, observed 2026-10-24)
- License: Apache 2.0 (friction: none). Permissive; patent grant. (license file, observed 2026-10-24)
- Created 2026-09-26, last modified 2026-10-22. (HF API, observed 2026-10-24)
| Pipeline tag | image-text-to-text |
|---|---|
| Library | transformers |
| Architectures | Qwen3_5ForConditionalGeneration |
| Model type | qwen3_5 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 2,213,239,072 · F32: 2,592 |
| Size band | M |
| MoE | no |
| Context length | 262,144 (config.json max_position_embeddings) |
| Papers | arXiv:2610.22131 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: supported · Qwen3_5ForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen3_5ForConditionalGeneration · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Hardware fit
3 estimates
Hardware fit ESTIMATE
Weights-only memory for Intern-Decision-2B: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 5.3 GB · Single GPU (<24 GB) |
|---|---|
| FP8 (1 byte/param) | 2.7 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 1.3 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Decision facts
catalog
Decision-model catalog curated
| How it was made | full fine-tune (whole weights published) |
|---|---|
| Lineage bucket | F - fine-tune of an open model (public/synthetic data) |
| Lineage evidence | board file inspection (adapter/head/weight files) + HF base_model field |
| Base model | Qwen/Qwen3.5-2B-Base |
| DI 0.2.1 score | 19.38 (independent (DI 0.2.1 board)) |
| ECE (board) | 0.0608 |
| Median latency | 33.5 ms (DI board, 1x RTX PRO 6000, single process) |
| Hosted price (input) | self-hosted/M |
| Source | https://huggingface.co/internlm/Intern-Decision-2B |
All variants
2 variants
Lineage
Base model: Qwen/Qwen3.5-2B
quantized: 2
Top variants (2 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| bombdefuser-124/Intern-Decision-2B-GGUF | quantized | GGUF | — | — | apache-2.0 | bombdefuser-124 | 1 | 831 |
| jersobh/jeff-2b-gguf | quantized | gguf | — | — | apache-2.0 | jersobh | 2 | 487 |
Repository changelog
4 commits
Repository changelog 4 commits
Papers
1 paper
Papers 1
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Similar models
3 models
Similar models
- Qwen3-VL-2B-Instruct · 2.13B same size band (M), same task (image-text-to-text), more providers, permissive license
- Qwen2-VL-2B-Instruct · 2.21B same size band (M), same task (image-text-to-text), permissive license
- Qwen3.5-2B · 2.27B same size band (M), same task (image-text-to-text), more providers, permissive license
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:43 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:17 UTC · Last verified 2026-10-25
Follow Intern-Decision-2B
Watch this model
- /feeds/models/internlm--Intern-Decision-2B.xml(RSS 2.0) · every change to Intern-Decision-2B
- /feeds/families/internlm--Intern.xml(RSS 2.0) · every change across the Intern family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.