Developer Utilities - a mmckinish Collection

mmckinish 's Collections

AI Benchmarks & Leaderboards Put things like:

Developer Utilities

AI Infrastructure

AI Architecture

Engineering Intelligence

Marketing & Media

Commercial Intelligence

Embeddings & Search

Website Experience

Document Intelligence

Commercial Experience AI

Developer Utilities

updated Aug 4

Developer Utilities

Running

Agents

269

Convert to Safetensors

🐶

269

Convert a Hugging Face model to Safetensors and open a PR
An Empirical Study of Safetensors' Usage Trends and Developers' Perceptions

Paper • 2501.02170 • Published Jan 4, 2025
Source files for GGUF, EXL2, AWQ, GPTQ, HQQ etc etc

Collection

Safetensor source files (by David_AU) to use directly and/or create different quants and/or merges. Link to GGUFS/full model card on each. • 54 items • Updated 1 day ago • 40
Running

94

GGUF Model VRAM Calculator

📈

94

Calculate VRAM requirements for LLM models
Unsloth Dynamic 2.0 Quants

Collection

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 123 items • Updated 5 days ago • 843
Mind the Gap: A Practical Attack on GGUF Quantization

Paper • 2505.23786 • Published May 24, 2025 • 1
Running on A10G

2.1k

GGUF My Repo

🦙

2.1k

Quantize Hugging Face models to GGUF format instantly
Gemma 3 QAT

Collection

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 21 • 218
APEX Quants (GGUF)

Collection

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 48 items • Updated about 1 month ago • 149
Quantized Models (GGUF, IQ, Imatrix)

Collection

Various GGUF quantizations of small models. Models with a "checkmark" are personal favorites. An "orange arrow" means it's being uploaded. • 97 items • Updated Mar 2 • 73
INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

Paper • 2510.25602 • Published Oct 29, 2025 • 81
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights

Paper • 2509.22944 • Published Sep 26, 2025 • 81
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13, 2025 • 184
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Paper • 2408.04682 • Published Aug 8, 2024 • 16
When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

Paper • 2606.05806 • Published Jun 4 • 25
mistralai/Codestral-22B-v0.1

22B • Updated Jul 24, 2025 • 19.9k • 1.36k
codestral

Collection

1 item • Updated May 6, 2025
Mamba-Codestral-7B-v0.1

Collection

1 item • Updated Dec 18, 2024
meta-llama/Llama-3.3-70B-Instruct

Text Generation • 71B • Updated Dec 21, 2024 • 312k • • 3.12k
meta-llama/Llama-3.3-70B-Instruct

Collection

1 item • Updated Jun 27, 2025 • 1
OpenHands/openhands-lm-32b-v0.1

Text Generation • 33B • Updated Apr 16, 2025 • 132 • 392
OpenHands/CodeScout-14B

Text Generation • 15B • Updated Mar 19 • 58 • • 4
CodeScout

Collection

RL-trained code search agents (1.7B, 4B, 14B) that outperform 2–18× larger models using only a Unix terminal. 📄 arxiv.org/abs/2603.17829 • 12 items • Updated Mar 19 • 9
OpenHands

Collection

0 items • Updated May 18
browser-use/bu-30b-a3b-preview

Image-Text-to-Text • 31B • Updated Apr 4 • 14.5k • 266
Browser Use

Collection

1 item • Updated Feb 27
crewai

Collection

1 item • Updated Aug 10, 2025
Autogen

Collection

1 item • Updated Sep 4, 2024 • 1
Claude Code

Collection

1 item • Updated Apr 30
Triton

Collection

1 item • Updated Oct 2, 2025 • 1
Triton

Collection

1 item • Updated Mar 9, 2025
gpt-oss

Collection

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 481
Whisper Release

Collection

Whisper includes both English-only and multilingual checkpoints for ASR and ST, ranging from 38M params for the tiny models to 1.5B params for large. • 12 items • Updated Sep 13, 2023 • 166
openai/gpt-oss-120b

Text Generation • 117B • Updated Aug 26, 2025 • 3.74M • • 5.38k
openai/gpt-oss-20b

Text Generation • 21B • Updated Aug 26, 2025 • 5.9M • • 5.15k
openai/whisper-large-v3

Automatic Speech Recognition • 2B • Updated Aug 12, 2024 • 3.74M • • 6.59k
openai/whisper-large-v3-turbo

Automatic Speech Recognition • 0.8B • Updated Oct 4, 2024 • 6.26M • • 3.43k