The AI Models Guide — What to Use for Every Task
A living guide to the AI model landscape: 50 tracked models grouped by task, weekly movement and the skills employers hire for — refreshed automatically.
10 min read
A living guide to the AI model landscape: 50 tracked models grouped by task, weekly movement and the skills employers hire for — refreshed automatically.
Quick Answer
Task-by-task guide to AI models, refreshed weekly from live data: 50 tracked models across LLMs, embeddings, vision and speech plus demand from 1,014 AI job lis
Search Snapshot
50 models tracked · snapshot 2026-08-02 · 1,014 active AI job listings analysed
Picking the right model starts with the task — not the name on a benchmark leaderboard. A model built for semantic search will underperform on speech transcription, and a large language model is overkill for text classification. This guide tracks 50 models across 8 families, refreshed every week from Hugging Face download data, so the numbers reflect real-world usage rather than marketing claims. Pair that with 1,014 active job listings and you get a clear picture of which model types matter in production and in hiring.
Work through these in order — most wrong choices come from starting at step 4.
| Model family | Use it for | Current leader |
|---|---|---|
| Text generation and LLMs | Chat assistants, coding copilots, agents, summarization, drafting and any task where the output is free-form text. | Qwen3-0.6B |
| Vision-language and multimodal | Describing images, reading documents and screenshots, answering questions about visual content and combining text with other media. | gemma-4-26B-A4B-it |
| Embeddings, search and ranking | Semantic search, RAG retrieval, deduplication, clustering and recommendation. Rerankers refine an initial result list for precision. | all-MiniLM-L6-v2 |
| Language understanding and classification | Sentiment analysis, topic and intent classification, named-entity recognition, translation and other structured judgements about text. | bert-base-uncased |
| Speech and audio | Transcription, voice interfaces, dubbing, meeting notes and audio event detection. | Kokoro-82M |
| Computer vision | Classifying images, detecting and segmenting objects, visual quality control and content moderation. | clip-vit-base-patch32 |
| Time series forecasting | Demand forecasting, anomaly detection and other predictions over numeric sequences and tables. | chronos-2 |
| Other specialist models | Niche tasks — protein folding, robotics, graph learning and research architectures that have not settled into a mainstream category. | electra-base-discriminator |
Use it for: Chat assistants, coding copilots, agents, summarization, drafting and any task where the output is free-form text.
Text generation and LLMs are dominated by compact, efficient models, with Qwen/Qwen3-0.6B leading at 28.3M downloads — nearly 11M ahead of facebook/opt-125m at 17.3M. The third spot goes to trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 at 15.5M downloads, signalling strong demand for small models suited to testing and edge deployment.
| Model | Maker | Task | Downloads | Likes | This week |
|---|---|---|---|---|---|
| Qwen3-0.6B | Qwen | text-generation | 28.3M | 1.5k | +1.6M |
| opt-125m | text-generation | 17.3M | 286 | +1.3M | |
| tiny-Qwen2ForCausalLM-2.5 | trl-internal-testing | text-generation | 15.5M | 18 | +1.9M |
| Qwen3-8B | Qwen | text-generation | 15.1M | 1.3k | — |
| Qwen2.5-1.5B-Instruct | Qwen | text-generation | 13.9M | 786 | +538.9k |
| gpt2 | openai-community | text-generation | 13.4M | 3.4k | — |
The largest and fastest-moving family. Frontier models (Claude, GPT, Gemini) are API-only; the open-weight models listed here are what you run yourself.
Use it for: Describing images, reading documents and screenshots, answering questions about visual content and combining text with other media.
Vision-language and multimodal hiring interest is converging on Google's Gemma 4 family, with the 26B sparse variant pulling 12.1M downloads and the 31B dense version close behind at 11.8M. Qwen/Qwen3.5-9B matches that 11.8M figure, showing that mid-size open models remain competitive against larger alternatives.
| Model | Maker | Task | Downloads | Likes | This week |
|---|---|---|---|---|---|
| gemma-4-26B-A4B-it | image-text-to-text | 12.1M | 1.3k | — | |
| gemma-4-31B-it | image-text-to-text | 11.8M | 3.4k | — | |
| Qwen3.5-9B | Qwen | image-text-to-text | 11.8M | 1.8k | +2.4M |
| Qwen2.5-VL-7B-Instruct | Qwen | image-text-to-text | 9.1M | 1.7k | — |
| Qwen3.6-35B-A3B-FP8 | Qwen | image-text-to-text | 8.3M | 334 | New |
Use these when the input is not just text — document extraction, chart reading and UI understanding all live here.
Use it for: Semantic search, RAG retrieval, deduplication, clustering and recommendation. Rerankers refine an initial result list for precision.
Embeddings, search and ranking are overwhelmingly led by sentence-transformers/all-MiniLM-L6-v2, which has accumulated 251.1M downloads — nearly three times the tally of second-place cross-encoder/ms-marco-MiniLM-L6-v2 at 86.8M. BAAI/bge-small-en-v1.5 rounds out the top three at 69.7M downloads, confirming that lightweight, general-purpose embedding models dominate production pipelines.
| Model | Maker | Task | Downloads | Likes | This week |
|---|---|---|---|---|---|
| all-MiniLM-L6-v2 | sentence-transformers | sentence-similarity | 251.1M | 5.2k | — |
| ms-marco-MiniLM-L6-v2 | cross-encoder | text-ranking | 86.8M | 293 | +1.6M |
| bge-small-en-v1.5 | BAAI | feature-extraction | 69.7M | 520 | +3.2M |
| paraphrase-multilingual-MiniLM-L12-v2 | sentence-transformers | sentence-similarity | 58.6M | 1.3k | +8.9M |
| bge-m3 | BAAI | sentence-similarity | 34.6M | 3.3k | — |
| all-mpnet-base-v2 | sentence-transformers | sentence-similarity | 25.9M | 1.3k | — |
The workhorse family behind almost every RAG system. Small, cheap to run and rarely the bottleneck — pick one with strong retrieval benchmarks and move on.
Use it for: Sentiment analysis, topic and intent classification, named-entity recognition, translation and other structured judgements about text.
Language understanding and classification is still anchored by google-bert/bert-base-uncased, which records 104.9M downloads and remains the default baseline for NLP classification tasks. google-t5/t5-small at 25.2M and FacebookAI/xlm-roberta-base at 21.9M show continued demand for sequence-to-sequence and multilingual understanding models respectively.
| Model | Maker | Task | Downloads | Likes | This week |
|---|---|---|---|---|---|
| bert-base-uncased | google-bert | fill-mask | 104.9M | 2.7k | +24.4M |
| t5-small | google-t5 | translation | 25.2M | 587 | — |
| xlm-roberta-base | FacebookAI | fill-mask | 21.9M | 876 | — |
| bge-reranker-v2-m3 | BAAI | text-classification | 18.9M | 1.1k | +1.1M |
| roberta-large | FacebookAI | fill-mask | 12.5M | 317 | — |
| roberta-base | FacebookAI | fill-mask | 11.5M | 632 | +2.6M |
BERT-family encoders remain heavily used in production because they are fast, cheap and deterministic to fine-tune for a fixed label set.
Use it for: Transcription, voice interfaces, dubbing, meeting notes and audio event detection.
Speech and audio generation is led by hexgrad/Kokoro-82M at 11.3M downloads, outpacing coqui/XTTS-v2 at 9.0M despite Kokoro being a far smaller model by parameter count. pyannote/speaker-diarization-3.1 sits at 8.6M downloads, reflecting steady real-world use of speaker separation in transcription and meeting-analytics workflows.
| Model | Maker | Task | Downloads | Likes | This week |
|---|---|---|---|---|---|
| Kokoro-82M | hexgrad | text-to-speech | 11.3M | 6.6k | +1.3M |
| XTTS-v2 | coqui | text-to-speech | 9.0M | 3.7k | — |
| speaker-diarization-3.1 | pyannote | automatic-speech-recognition | 8.6M | 2.9k | +174.6k |
| whisper-large-v3-turbo | openai | automatic-speech-recognition | 8.5M | 3.2k | New |
Speech-to-text (ASR) and text-to-speech are separate model families — most voice products chain one of each around an LLM.
Use it for: Classifying images, detecting and segmenting objects, visual quality control and content moderation.
Computer vision download volume is shaped by CLIP, with openai/clip-vit-base-patch32 at 22.9M and openai/clip-vit-large-patch14 at 8.9M together accounting for the majority of top-three traffic. timm/mobilenetv3_small_100.lamb_in1k at 18.1M sits between them, showing strong appetite for lightweight classification backbones in production vision systems.
| Model | Maker | Task | Downloads | Likes | This week |
|---|---|---|---|---|---|
| clip-vit-base-patch32 | openai | zero-shot-image-classification | 22.9M | 992 | — |
| mobilenetv3_small_100.lamb_in1k | timm | image-classification | 18.1M | 99 | — |
| clip-vit-large-patch14 | openai | zero-shot-image-classification | 8.9M | 2.1k | — |
Zero-shot vision models classify against labels you supply at runtime — no retraining needed when categories change.
Use it for: Demand forecasting, anomaly detection and other predictions over numeric sequences and tables.
Time series forecasting is consolidating around Amazon's Chronos ecosystem, with amazon/chronos-2 recording 25.7M downloads and autogluon/chronos-bolt-small reaching 13.2M. autogluon/chronos-2 adds another 12.0M downloads, meaning the three leaders are effectively variants of the same model lineage — a rare degree of concentration in any model category.
| Model | Maker | Task | Downloads | Likes | This week |
|---|---|---|---|---|---|
| chronos-2 | amazon | time-series-forecasting | 25.7M | 385 | +11.1M |
| chronos-bolt-small | autogluon | time-series-forecasting | 13.2M | 58 | — |
| chronos-2 | autogluon | time-series-forecasting | 12.0M | 47 | +1.7M |
Foundation models for time series are a recent arrival — they forecast series they were never trained on, the way LLMs handle unseen text.
Use it for: Niche tasks — protein folding, robotics, graph learning and research architectures that have not settled into a mainstream category.
Specialist models outside core categories are led by google/electra-base-discriminator at 53.8M downloads, a figure that reflects its widespread use as a discriminator backbone in training pipelines rather than standalone inference. lpiccinelli/unidepth-v2-vitl14 at 30.2M and Bingsu/adetailer at 10.3M round out the group, spanning monocular depth estimation and image post-processing respectively.
| Model | Maker | Task | Downloads | Likes | This week |
|---|---|---|---|---|---|
| electra-base-discriminator | — | 53.8M | 147 | — | |
| unidepth-v2-vitl14 | lpiccinelli | — | 30.2M | 47 | +16.8M |
| adetailer | Bingsu | — | 10.3M | 755 | — |
This week's snapshot added four models: Qwen/Qwen3-32B, Qwen/Qwen3.6-35B-A3B-FP8, openai/whisper-large-v3-turbo and openai/gpt-oss-20b. The biggest growth stories were google-bert/bert-base-uncased adding 24.4M downloads in a single week and lpiccinelli/unidepth-v2-vitl14 surging 16.8M, signalling strong demand at both ends of the model-size spectrum.
| New in the tracked set | Task | Downloads |
|---|---|---|
| Qwen/Qwen3-32B | text-generation | 9.2M |
| openai/whisper-large-v3-turbo | automatic-speech-recognition | 8.5M |
| Qwen/Qwen3.6-35B-A3B-FP8 | image-text-to-text | 8.3M |
| openai/gpt-oss-20b | text-generation | 8.3M |
| Fastest download growth | Task | Added this week |
|---|---|---|
| google-bert/bert-base-uncased | fill-mask | +24.4M |
| lpiccinelli/unidepth-v2-vitl14 | — | +16.8M |
| amazon/chronos-2 | time-series-forecasting | +11.1M |
| sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 | sentence-similarity | +8.9M |
| BAAI/bge-small-en-v1.5 | feature-extraction | +3.2M |
| FacebookAI/roberta-base | fill-mask | +2.6M |
| Qwen/Qwen3.5-9B | image-text-to-text | +2.4M |
| trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 | text-generation | +1.9M |
Embeddings, search and ranking models and language understanding models map directly to the skill employers ask for most — Machine Learning, which appears in 1,372 job listings. LLMs and GenAI skills follow at 778 listings, reflecting the 12 text generation models tracked here, while AI Agents demand at 368 listings shows that orchestration around these models is becoming its own hiring category.
| Skill | Active listings |
|---|---|
| Machine Learning | 1372 |
| LLMs / GenAI | 778 |
| AI Agents | 368 |
| AWS | 194 |
| Azure | 156 |
| Deep Learning | 152 |
| Fine-tuning | 146 |
| A/B Testing | 128 |
| Agile / Scrum | 126 |
| GCP | 110 |
| Kubernetes | 88 |
| CI/CD | 75 |
Explore the full demand data on the AI and ML job market page or track movement over time on skill trends.
Model popularity comes from a weekly snapshot of Hugging Face download and like counts (50 top models, latest snapshot 2026-08-02). "This week" columns compare the latest snapshot with one taken roughly a week earlier, so they show download velocity rather than all-time totals. Employer demand comes from daily analysis of active AI job listings (1,014 at last count). Frontier API-only models do not appear in download tables because they publish no open weights — that is a limitation of the source, not a quality judgement.
For RAG and semantic search, sentence-transformers/all-MiniLM-L6-v2 is the most widely adopted starting point, sitting at 251.1M downloads. If you need multilingual retrieval, sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 is gaining fast, adding 8.9M downloads this week alone.
The most downloaded AI model in this snapshot is sentence-transformers/all-MiniLM-L6-v2 at 251.1M total downloads. It belongs to the embeddings, search and ranking family — the largest tracked group at 13 models — which reflects how central vector search has become to production AI systems.
Machine Learning is the most requested skill across the 1,014 job listings tracked, appearing in 1,372 listings, followed by LLMs and GenAI at 778 and AI Agents at 368. Cloud platforms also feature prominently, with AWS at 194 listings and Azure at 156, meaning model knowledge paired with deployment experience is what most employers are actually hiring for.
Updated August 17, 2026. This guide regenerates automatically from fresh data every week.
Continue with adjacent guides and tactical breakdowns.
Actionable guides, market updates and shipping notes — once a week.