Qwen3.6-35B-A3B-NVFP4-Fast
unsloth · Kit
Serves Qwen3.6 35B A3B in a fast NVFP4 build by Unsloth for vLLM on NVIDIA GPUs. The card says it has 1.79x the throughput of other NVFP4 builds and fits a 32…
New
AI skills and agents for developers
Prompts, coding agent briefs and kits for writing and reviewing code with fewer tokens.
Categories and filters
Listings
Ornith-1.5-122B-NVFP4-DFlash2-RTX-Spark
Sherlock-Comms · Kit
Serves the 122B Ornith 1.5 model through vLLM with DFlash2 speculative decoding, using an unquantized output head. Made for RTX Spark laptops with 128 GB of me…
New
Qwen3.8-27B-QUASAR-NVFP4
QUASAR-QAT · Kit
Runs Qwen3.8-27B in 4-bit NVFP4 at 19.7 GB, trained with the QUASAR method to stay close to the full BF16 model. For people serving it with vLLM on an NVIDIA B…
New
DeepSeek-V4.1-Flash-1017-EXL3-franken-v100
philbert440 · Kit
Runs DeepSeek V4.1 Flash at its full 1M-token context on eight Tesla V100 32 GB cards, using an EXL3 expert pack and an SM70 vLLM build. For owners of such ser…
New
Leanstral 1.5 119B A6B
mistralai · Kit
An open code-agent model from Mistral for the Lean 4 proof assistant. It proves theorems and fixes Lean code, takes text and images, and runs through the Mistr…
New
Qwen3.8-27B-NVFP4 Deployment Edition
IteraCompute · Kit
Serves Qwen3.8-27B in NVFP4 on one RTX 5090 with vLLM, with a checksum-verified download, FP8 KV cache, tool calls and reasoning support. For developers self-h…
New
Qwen3.6-35B-A3B-2Bit-GSQ
ISTA-DASLab · Kit
A 2-bit quantized copy of Qwen3.6-35B-A3B made with GSQ, a Gumbel-Softmax method, that keeps most reasoning and coding ability at a much smaller memory footpri…
New
KVARK Sparkle 1.0 (27B) FP8
Egzakta · Kit
Runs a 27B model that reads images and text, in FP8 for vLLM. It reasons with far fewer tokens than a Qwen model of the same size. Made for people who host the…
New
Qwen3.8-27B-NVFP4-DGX-SPARK
autotrust · Kit
Speeds up Qwen3.8-27B NVFP4 decoding about 3.9 times on a DGX Spark, using the same weights and a tuned speculative-decoding setup. For teams serving it with v…
New
OvisOCR2
ATH-MaaS · Kit
Document parsing model that reads a page image and writes Markdown in reading order, covering text, formulas and tables. About 0.8B parameters, run through vLL…
New
Qwen3.8-27B-Quark-AWQ-MXFP4
amd · Kit
Runs Qwen3.8-27B as a smaller MXFP4-quantized copy made with AMD Quark and AWQ, served through vLLM. Made for developers who want a compressed 27B vision-langu…
New
Bielik-11B-v3.1-DFlash2
speakleash · Kit
Pairs with the Bielik-11B-v3.1-Instruct model as a draft model for speculative decoding in SGLang or vLLM. It is not a standalone language model.
New
Bielik-11B-v3.1-DFlash
speakleash · Kit
Serves as the DFlash draft model that pairs with Bielik-11B-v3.1-Instruct for speculative decoding in SGLang or vLLM. It is not a standalone language model. Fo…
New
Comet 60B
MultiverseComputingCAI · Kit
A 61.1B multimodal model from Multiverse Computing, a compressed version of NVIDIA's Nemotron 3.5 Super that takes text, image and video and keeps about 12B pa…
New
KAT-Coder-V2.5-Dev
Kwaipilot · Kit
An open-weight coding model from Kwaipilot, a mixture-of-experts with 35B total and 3B active parameters, tuned for agentic coding and fewer tool-call glitches…
New
Qwen3.8-27B-DFlash2 by incoai
incoai · Kit
Speeds up Qwen3.8-27B by drafting blocks of tokens that the main model then checks, with output unchanged. A 1.9B draft model for SGLang and vLLM servers, not…
New
MedErtas v0.1 31B LS
ErtasAI · Kit
Serves a medical-domain language model, a compressed Gemma 4 31B, on vLLM and NVIDIA Blackwell GPUs. Built for medical AI products that need fast, low-cost ans…
New
Qwen3.8-27B-AWQ-INT4
cyankiwi · Kit
A 4-bit AWQ quantization of Qwen3.8-27B by cyankiwi, a 27B vision-language model with thinking control. Weights are 21.02 GB and load in Transformers, vLLM or…
New
Ling-3.1-flash-1019
inclusionAI · Kit
Handles scientific and agentic tasks with 560B total and 25B active parameters and a 1M-token context, tuned further from Ling-3.1-flash. Serving examples use…
New
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…
New