Qwen3.5 2B text-only GGUF models compressed by TurinTech with Artemis. Recommended: Qwen3.5-2B-Artemis-Q5_K_M.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF. Download size is not runtime memory. Measured Q5_K_M: Mean KLD 0.0073, Same top p 95.0% vs BF16 on WikiText-2 test; protocol rtx5090-2026-10-23.
Qwen3.5 2B text-only GGUF models compressed by TurinTech with Artemis. Recommended: Qwen3.5-2B-Artemis-Q5_K_M.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF. Download size is not runtime memory. Measured Q5_K_M: Mean KLD 0.0073, Same top p 95.0% vs BF16 on WikiText-2 test; protocol rtx5090-2026-10-23.
Qwen3.5 2B text-only GGUF models compressed by TurinTech with Artemis. Recommended: Qwen3.5-2B-Artemis-Q5_K_M.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF. Download size is not runtime memory. Measured Q5_K_M: Mean KLD 0.0073, Same top p 95.0% vs BF16 on WikiText-2 test; protocol rtx5090-2026-10-23.
Qwen3.5 2B text-only GGUF models compressed by TurinTech with Artemis. Recommended: Qwen3.5-2B-Artemis-Q5_K_M.gguf. Model files, checksums and measured trade-offs: https://huggingface.co/turintech/Qwen3.5-2B-Artemis-GGUF. Download size is not runtime memory. Measured Q5_K_M: Mean KLD 0.0073, Same top p 95.0% vs BF16 on WikiText-2 test; protocol rtx5090-2026-10-23.