GLM-5.3-Flash GGUF quantized models by 6block
6block
company
Verified
AI & ML interests
None defined yet.
Qwen3.8-27B (dense, vision) imatrix GGUF: 18 tiers plus q8_0/f16 mmproj and an MTP draft. More Qwen3.8 sizes as they land.
Moonshot Kimi-K3 GGUF quants, imatrix-calibrated. For llama.cpp / Ollama / LM Studio.
NVFP4 text encoder for MiniMax-H3 video generation: the Qwen3-VL encoder quantized to run in ComfyUI on a single card.
Sub-4-bit GGUF quants of DeepSeek-V4: Flash-0731 (seven PPL-tested tiers + DSpark draft) and Pro-0813 (1.57T, factory FP4 master).
All Qwen3 quantized builds: GGUF, FP8, AWQ and GPTQ. Covers 4B to 32B dense and 30B-A3B MoE.
GLM-5.3-Flash GGUF quantized models by 6block
NVFP4 text encoder for MiniMax-H3 video generation: the Qwen3-VL encoder quantized to run in ComfyUI on a single card.
Qwen3.8-27B (dense, vision) imatrix GGUF: 18 tiers plus q8_0/f16 mmproj and an MTP draft. More Qwen3.8 sizes as they land.
Sub-4-bit GGUF quants of DeepSeek-V4: Flash-0731 (seven PPL-tested tiers + DSpark draft) and Pro-0813 (1.57T, factory FP4 master).
Moonshot Kimi-K3 GGUF quants, imatrix-calibrated. For llama.cpp / Ollama / LM Studio.
All Qwen3 quantized builds: GGUF, FP8, AWQ and GPTQ. Covers 4B to 32B dense and 30B-A3B MoE.