datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
AXXXX_jssp_policy_step_train_dispatch_v1needle2-harness-dispatch
Needle-2 Harness-Dispatch Corpus (review build)
Eval/training corpus for tool-dispatch on a developer-agent harness surface
(8 tools: bash / read / write / edit / glob / grep / web_search /
todo_write). This is a review build — every record carries QA
annotations so a human can approve, relabel, or flag before the next
training run.
Provenance
Generated and judged by glm-5.3 , two
generation rounds (seeds 7 and 101), judge pass kept/fixed/dropped.
1,307 raw… See the full description on the dataset page: https://huggingface.co/datasets/ebowwa/needle2-harness-dispatch.localagent-dispatch-data
LocalAgent Dispatch Data
Synthetic data for training/evaluating a generable tool-dispatch model over a 50-tool surface
(route head → dense selector → pointer-copy). A static snapshot of the deterministic generators in
LocalAgent (src/localagent/data/). Train/eval are
disjoint in both phrasing and slot values. Companion model + demo:
danelcsb/localagent-tiny-30m-byte ·
Space.
Configs
config
rows (train/eval)
what it is
paraphrase
1000 / 1000
many natural… See the full description on the dataset page: https://huggingface.co/datasets/danelcsb/localagent-dispatch-data.Arabic-Mobile-Instructions
Arabic Mobile Instructions
A curated Arabic instruction dataset designed for training and evaluating mobile-optimized language models.
Why Arabic?
Arabic is spoken by 400+ million people across 22 countries, yet Arabic-language instruction data on HuggingFace is scarce. This dataset fills the gap with mobile-relevant tasks:
Summarization — رسائل، إيميلات، إشعارات
Classification — تصنيف الرسائل والمشاعر
Translation — ترجمة بين العربية والإنجليزية
Question… See the full description on the dataset page: https://huggingface.co/datasets/dispatchAI/Arabic-Mobile-Instructions.performance-tiers
Performance Tiers
Models grouped by speed:
Ultra Fast (30+ t/s): 1 models
Fast (15-30 t/s): 9 models
Moderate (5-15 t/s): 16 models
Slow (<5 t/s): 5 models
🚀 dispatchAI
usage-examples
Usage Examples
Copy-paste code examples for each verified dispatchAI model.
Includes Python (llama-cpp-python), SDK (dispatchai), and CLI (llama.cpp) examples.
🚀 dispatchAI
model-categories
Model Categories
31 working models organized by use case.
🚀 dispatchAI
AXXXX_jssp_mixed_step_train_dispatch_v1tiny-dispatch-coach-traces
Tiny Dispatch Coach Traces
This dataset shares the sanitized build trace for Tiny Dispatch Coach, a Build
Small Hackathon project.
The trace records the model/planner design:
OpenBMB MiniCPM5-1B-GGUF parses dispatcher notes into constraints when the
optional llama.cpp path is enabled.
A deterministic planner computes route splits, time windows, wait time,
lateness, and baseline deltas.
The sample data is synthetic.
No API keys, user emails, real customer records, company… See the full description on the dataset page: https://huggingface.co/datasets/build-small-hackathon/tiny-dispatch-coach-traces.MobileBench
MobileBench: The On-Device LLM Benchmark
A standardized evaluation benchmark designed specifically for mobile and edge-deployed language models.
Why MobileBench?
Existing benchmarks (MMLU, HumanEval, GSM8K) test what large models can do on servers. MobileBench tests what small models can do on phones — the tasks users actually perform:
Summarization — The #1 on-device task (messages, emails, notifications)
Classification — Spam detection, sentiment, intent… See the full description on the dataset page: https://huggingface.co/datasets/dispatchAI/MobileBench.code-generation-eval
Code Generation Evaluation
5 code generation tasks for evaluating dispatchAI coder models.
Best models: Qwen2.5-0.5B-Coder-mobile, Qwen2.5-Coder-1.5B-mobile
🚀 dispatchAI
function-calling-eval
Function Calling Evaluation
5 function-calling tasks for evaluating dispatchAI function-calling models.
Note: Llama-3.2-1B-FunctionCall has ~33% success rate on these tasks.
🚀 dispatchAI
per-chip-benchmark-matrix
Per-Chip Benchmark Matrix
On-device inference benchmarks for mobile LLMs across chipsets.
Overview
This dataset contains real on-device inference benchmarks for 8 mobile-optimized
models running on Samsung S20 FE 5G phones (Snapdragon 865, 8GB RAM, Android 13).
Contents
benchmark_matrix.csv — Tabular data: model, device, chipset, tokens/sec, size
benchmark_matrix.json — Full structured data including hardware specs and methodology
Key… See the full description on the dataset page: https://huggingface.co/datasets/dispatchAI/per-chip-benchmark-matrix.chat-format-reference
Chat Format Reference
Correct chat formats for dispatchAI GGUF models. Use with llama-cpp-python's chat_format parameter.
Usage
from llama_cpp import Llama
llm = Llama(model_path='model.gguf', chat_format='llama-3') # For SmolLM2/Llama-3.2
🚀 dispatchAI
inference-test-suite
Inference Test Suite
Standardized test suite for verifying dispatchAI models.
🚀 dispatchAI
cost-analysis
Cost Analysis
Cloud API vs on-device inference cost comparison.
At 10K queries/day: Save $18,249/year with on-device.
At 100K queries/day: Save $182,499/year.
🚀 dispatchAI
on-device-latency
On-Device Latency Benchmark
Real-world inference latency data for mobile-optimized LLMs, measured on actual phone hardware.
Hardware
Spec
Value
Device
Samsung S20 FE 5G
SoC
Snapdragon 865
RAM
8GB
OS
Android 13
Runtime
llama.cpp (4 threads)
Metrics
tokens_per_sec — Generation speed during inference
latency_ms_per_token — Time per generated token
ram_usage_mb — Peak RAM during inference
file_size_mb — GGUF model file size… See the full description on the dataset page: https://huggingface.co/datasets/dispatchAI/on-device-latency.hardware-profiles
Hardware Profiles
Phone hardware profiles for estimating mobile LLM inference speed.
Snapdragon 865 (Samsung S20 FE) is the verified baseline.
🚀 dispatchAI
mobile-task-prompts
Mobile Task Prompts
20 standardized prompts for evaluating mobile LLMs across 8 categories: summarization, classification, QA, translation, code, creative, math, function calling.
Use with dispatchAI models for consistent benchmarking.
🚀 dispatchAI
speed-ranking
Speed Ranking
All 31 working dispatchAI models ranked by CPU inference speed.
🚀 dispatchAI
paper-reengineering-mobile-models
Paper: Re-engineering 40+ Models with an Autonomous Agent
This dataset contains the paper and reproducibility data for:
"Re-engineering 40+ Models with an Autonomous Agent: A Zero-Cost Mobile AI Pipeline"
Contents
paper.md — Full paper text
inventory.json — Model inventory and pipeline metadata
Abstract
We present a fully autonomous pipeline that re-engineers open-source language models
for mobile and edge deployment at zero cost. Over 40 models… See the full description on the dataset page: https://huggingface.co/datasets/dispatchAI/paper-reengineering-mobile-models.error-patterns
Error Patterns
Common errors when running mobile LLMs and their fixes.
🚀 dispatchAI
speed-benchmark
Speed Benchmark
CPU inference speed for all 22 verified dispatchAI models.
Measured with llama-cpp-python (8 threads, 512 context).
🚀 dispatchAI
all-verified-benchmarks
All Verified Benchmarks
Real CPU benchmark data for ALL 31 working dispatchAI models.
Zero broken models. Zero partial models. All verified.
🚀 dispatchAI
silicon-profiling-snapdragon865
Real-Device Silicon Profiling: Snapdragon 865
Per-device inference benchmarks on real Samsung S20 FE 5G phones (Snapdragon 865).
No simulation. Real ARM CPU inference.
Hardware
Property
Value
Chipset
Qualcomm Snapdragon 865 (SM8250)
CPU
Kryo 585: 1x2.84GHz + 3x2.42GHz + 4x1.80GHz
GPU
Adreno 650
NPU
Hexagon Tensor Accelerator
RAM
8GB LPDDR5 (7.47GB total, 3-3.7GB free)
Device
Samsung Galaxy S20 FE 5G (SM-G981V)
Devices connected
39… See the full description on the dataset page: https://huggingface.co/datasets/dispatchAI/silicon-profiling-snapdragon865.model-comparison
Model Comparison: Original vs Mobile
Shows the size reduction achieved by dispatchAI's re-engineering.
Model
Original
Mobile
Reduction
SmolLM2-135M
270MB
101MB
62.6%
Qwen2.5-0.5B
1000MB
469MB
53.1%
Llama-3.2-1B
2500MB
770MB
69.2%
🚀 dispatchAI
detailed-comparison
Detailed Comparison
Real verified data for all 31 working models. Includes speed-per-MB efficiency metric.
🚀 dispatchAI
model-selection-guide
Model Selection Guide
Pick the right dispatchAI model for your use case.
🚀 dispatchAI
dispatch-7b-dataquantization-guide
Quantization Guide
Reference for choosing the right GGUF quantization level for mobile deployment.
Q4_K_M is the recommended sweet spot — 40% of FP16 size, 92% quality.
🚀 dispatchAI