models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Marlin-2BTinyLlama-1.1B-Chat-v1.0-marlinTinyLlama-1.1B-Chat-v1.0-GPTQ-Marlin-4bitmarlowe-22bQwen3.8-27B-Heretic-GPTQ-W4A16-G128-MarlinQwen3.5-4B-SX8Qwen3.8-27B-SX8UsernameJustAnother-Nemo-12B-Marlin-v8-GGUFMarlin-2B-ungatedllama7b-one-shot-2_4-w4a16-marlin24-tMiniCPM4.1-8B-MarlinMiniCPM4-8B-marlin-Eagle-vLLMMiniCPM4-8B-marlin-vLLMmarlin-2B-GPTQ-4BITSMiniCPM4-8B-marlin-cpmcuzephyr-7b-beta-marlinzephyr-7b-beta-channelwise-marlinMeta-Llama-3-70B-Instruct-MarlinNemo-12B-Marlin-v5tinyllama-marlin24-w4a16-group128llama7b-one-shot-2_4-w4a16-marlin24-t-altTinyLlama-1.1B-Chat-v1.0-g128-marlintinyllama-24-marlin24-4bit-g128tinyllama-24-marlin24-8bit-g128GLM-4.7-Flash-Marlin-MMFP4dbrx-base-converted-v2-4bit-gptq-marlinllama-2-7b-chat-marlindbrx-base-converted-v2-4bit-gptq-marlin-v2phi-2-super-marlinPhi-3-mini-4k-instruct-Q5_K_M-GGUF