Collection of Qwen3.8-27B quantizations, fine-tunes, and speculative decoding models.
Jake
jakeatx
AI & ML interests
distillation, MoE tuning + optimizing, offloading
Recent Activity
updated a collection 3 days ago
Qwen3.8-27B Models updated a collection 3 days ago
Qwen3.8-27B Models updated a model 3 days ago
jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-IQ4_XS-M-GGUFOrganizations
None yet
Qwen3.8 Perian checkpoints: 48->32 layers, 384->288 experts, 50% PLE, and rank-32 QLoRA on 12,558 math, agentic, and coding traces.
-
jakeatx/ream-288-rank32-3m-adapter
Text Generation • Updated • 366 • 1 -
jakeatx/slimder-qwen38-ream288-ngram50-mixed-recovery-qlora-v2
Text Generation • Updated • 45 -
jakeatx/slimder-qwen38-ream288-depth32-agentic-ngram50-mixed-nvfp4-v2
Text Generation • 57B • Updated • 745 -
jakeatx/Qwopus3.8-27B-Flash-ATX-IQ4_XS-M-GGUF
Text Generation • 27B • Updated • 1.33k • 2
Collection of Qwen3.8-27B quantizations, fine-tunes, and speculative decoding models.
Qwen3.8 Perian checkpoints: 48->32 layers, 384->288 experts, 50% PLE, and rank-32 QLoRA on 12,558 math, agentic, and coding traces.
-
jakeatx/ream-288-rank32-3m-adapter
Text Generation • Updated • 366 • 1 -
jakeatx/slimder-qwen38-ream288-ngram50-mixed-recovery-qlora-v2
Text Generation • Updated • 45 -
jakeatx/slimder-qwen38-ream288-depth32-agentic-ngram50-mixed-nvfp4-v2
Text Generation • 57B • Updated • 745 -
jakeatx/Qwopus3.8-27B-Flash-ATX-IQ4_XS-M-GGUF
Text Generation • 27B • Updated • 1.33k • 2