IQuest-Q1 GGUF conversion with recursive MTP and validation, plus an unmodified mirror of the original FP8 release.
AI & ML interests
None defined yet.
Recent Activity
Quantized versions of IQuest-Coder-V1-14B-Thinking (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-14B-Base-Stage1 (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-7B-Thinking (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-7B-Base-Stage1 (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-40B-Thinking (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-14B-Instruct (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-14B-Base (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-7B-Instruct (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-7B-Base (GGUF, FP8, INT4, INT8,mlx-8bit).
IQuest-Q1 GGUF conversion with recursive MTP and validation, plus an unmodified mirror of the original FP8 release.
Quantized versions of IQuest-Coder-V1-40B-Thinking (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-14B-Thinking (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-14B-Instruct (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-14B-Base-Stage1 (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-14B-Base (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-7B-Thinking (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-7B-Instruct (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-7B-Base-Stage1 (GGUF, FP8, INT4, INT8,mlx-8bit).
Quantized versions of IQuest-Coder-V1-7B-Base (GGUF, FP8, INT4, INT8,mlx-8bit).