huggingface-best

Topics in the source

• HuggingFace Best Model Finder
• Step 1: Parse the request
• Device → max parameter budget
• Step 2: Find relevant benchmark datasets
• Step 3: Fetch top models from leaderboards
• Step 4: Enrich with model metadata
• Step 5: Filter and rank
• Step 6: Output

Finds the best models for a task by querying official HF benchmark leaderboards, enriching results with model size data, filtering for what fits on the user's device, and returning a comparison table with benchmark scores. -- Extract from the user's message: Task: what they want the model to do (coding, math/reasoning, chat, OCR, RAG/retrieval, speech recognition, image classification, multimodal, agents, etc.) Device: hardware constraints (MacBook M-series 8/16/32/64GB unified memory, RTX GPU with VRAM amount, CPU-only, cloud/no constraint, etc.) If device is not mentioned, skip filtering entirely and return the highest-performing models regardless of size. If the task is genuinely ambiguous, ask one clarifying question. When a device is specified, extract its available memory (unified RAM for Apple Silicon, VRAM for discrete GPUs) and apply: fp16 max params (B) ≈ memory (GB) ÷ 2 Q4 max params (B) ≈ memory (GB) × 2 Examples: 16GB → 8B fp16 / 32B Q4 — 24GB VRAM → 12B fp16 / 48B Q4 — 8GB → 4B fp16 / 16B Q4 -- Fetch the full list of official HF benchmarks: Read the returned list and select the datasets most relevant to the user's task — match on dataset id, tags, and description. Use

This is an excerpt. Refer to the complete source and its current requirements.