AI projects from Hugging Face

DataWorld-35B-A3B

Zhanli-Li · Kit

A Qwen3.6-35B-A3B model tuned with multi-turn agentic reinforcement learning on the DataWorld tasks, for tool-calling agents. For teams serving a large mixture…

MiMo-V2.6-Distill-Qwen-9B-GSQ-RCO-GGUF

sainez · Kit

Gives you a 9B coding and tool-calling model as one 3.64 GiB GGUF file, quantized at about 3.5 bits per weight for running on your own machine.

LFM2.5-350M-home-assistant-sft

OrdenWills · Kit

Turns plain home commands such as turn off the TV into structured tool calls, checking device states first. A 350M model for smart home builders and tinkerers.

Qwen 3.6 35B-A3B REAP-48 v2 GGUF

crucible-labs · Kit

Runs a pruned and quantized Qwen3.6-35B-A3B in an 8.78 GiB GGUF file for llama.cpp, closer to the unquantized weights than the first release. For people with l…

MiniCPM5-2B-GGUF by bartowski

bartowski · Kit

Quantized GGUF copies of the MiniCPM5-2B text model in many sizes, made with llama.cpp and an importance matrix. For people running a small English and Chinese…

granite-4.2-3b-GGUF

bartowski · Kit

Quantized GGUF copies of IBM's granite-4.2-3b text model, in many sizes from full precision down to small 3-bit files. For people who run a small chat model on…

MiMo-V2.6-Flash-RL-NVFP4

primitive-ai · Kit

Serves Xiaomi's MiMo-V2.6-Flash-RL as an NVFP4 build for Blackwell GPUs, with the release's exact expert values and more throughput on two 96 GB cards. For peo…

auto-150m-3

ProCreations · Kit

Decides whether a coding agent's proposed tool call should run, answering approve or deny from the call, the request and the history. The smallest Auto model,…

gemma-4-E4B-it-weight-space-programming

jstarks · Kit

Google's Gemma 4 E4B-it with 0.002% of its weights edited directly, no training, to fix stalls in thinking mode with tool calls and multi-step math. Also ships…

Spark-X2.6-4B-AgentFast

JamieBradfield · Kit

Calls tools and follows instructions with almost no thinking delay, as a 4.1B fine-tune of Spark-X2.6-4B. Made for people building fast local agents that need…

granite-4.2-3b

ibm-granite · Kit

Reasons step by step before it answers, with tool calling, code generation and multilingual chat, in a compact 3B model from IBM. Supports a 128K context nativ…

Rein-NPC-4B

jmc0 · Kit

Drives game characters that hold a conversation, take in-game actions such as selling an item or calling guards, and stay in character under pressure. For game…

Granite-4.2-30B

ibm-granite · Kit

Works through a problem in steps before it answers, for math, code, tool calling and multilingual chat. IBM's largest dense Granite 4.2 model, under Apache 2.0…

gnani-evon-v3.3-30B-A3B

gnani · Kit

Chats, answers questions and reasons in English and ten Indic languages with a 128K context. A 30B mixture-of-experts model from Gnani.ai, for teams building a…

Qwen3.8-27B-Randean-MXFP4

flechin · Kit

A 27B reasoning model tuned to answer plainly instead of hedging, quantized to MXFP4 so vLLM can serve it on a single 32 GB GPU, for developers who run local r…

MiniCPM5-2B-GGUF

openbmb · Kit

Gives you MiniCPM5-2B, a small dense text model for English and Chinese, as GGUF files for on-device and local use. Suits people who want a compact model for c…

Needle 2

Cactus-Compute · Kit

A 45M-parameter open model for tool calling, device use and structured extraction, packed into one 14 MB binary that runs in about 28 MB of RAM. For developers…

Qwen Sharp Chat Templates

peculiar-ragdoll · Kit

Replaces the chat template of Qwen3.5, 3.6 and 3.8 models so they think less before answering and write tighter replies. For people running Qwen locally for co…

Granite-4.2-8B

ibm-granite · Kit

Reasons step by step, writes code, calls tools and chats in several languages with a context of up to 128K tokens, extendable to 512K. IBM's dense 8B model, fo…

CherryPit-1.2-2B

DRUPEs · Kit

A 2B coding and chat model built on MiniCPM5-2B that is much better at web apps needing several features in one component. For developers who want a small loca…

Raon-1 mini

KRAFTON · Kit

Chats and reasons, with a strength in Korean, and runs tool-calling agent tasks. A 28.8B mixture-of-experts model that activates 4.3B parameters per token with…

Needle 3

Cactus-Compute · Kit

A small on-device model from Cactus Compute for tool calling, structured extraction and text embeddings, used through the cactus Python package. For developers…

MiniCPM5-2B

openbmb · Kit

Generates text with a dense 2B-class model made for on-device and local use, covering coding, math, long context, tool use and agent tasks in English and Chine…

Qwen-Fixed-Chat-Templates

froggeric · Kit

Swaps Qwen's official chat templates for one drop-in Jinja file that fixes rendering errors, cache invalidation, wasted tokens and agent stalls. For people who…

BotPsy-0.8B

qvac · Kit

A small 0.8B model for function calling and agent workflows, built on Qwen3.5-0.8B and light enough to run on a device, for developers who want a local assista…

BotPsy-0.8B-GGUFs

qvac · Kit

GGUF copies of the 0.8B BotPsy tool-calling model in BF16, Q8_0 and Q4_K_M, for running agent and function-calling work fully on your own device with llama.cpp.