ltejedor / deepseek-v4.1-flash

DeepSeek V4.1 Flash 1017 (LibertAIDAI EXL3 3.5 bpw + official Engram tables) served with exllamav3 on 2x A100 80GB. Greedy chat; prompt up to 2,048 tokens, prompt + output up to 4,096. A cold start takes about 8-12 minutes.

16 runs
Public

ltejedor / hf2rep-diag-mw-a100x2

Diagnostic probe for Cog managed-weights delivery (hf2rep investigation). Not a usable model.

2 runs
Public

ltejedor / hf2rep-diag-a100x2

Diagnostic probe for infrastructure measurements (hf2rep investigation). Not a usable model.

48 runs
Public

ltejedor / qwen3.8-27b-0.1

Qwen3.8 27B served with vLLM

97 runs
Public

ltejedor / qwen3.8-27b

Qwen3.8 27B served with vLLM

0 runs
Public

ltejedor / qwen3.8-27b-old

Qwen3.8 27B served with vLLM

0 runs
Public

ltejedor / differentiable-rasterizer-vector-graphics

Controllable generative AI art

601 runs
Public

ltejedor / cmf

Stable Diffusion model fine-tuned on Color, Material, and Finish samples

226 runs
Public

ltejedor / prolific-splats

image to 3D

93 runs
Public

ltejedor / stable_​diffusion_​individual_​letters

409 runs
Public

ltejedor / sundai-fonts-letters-together

118 runs
Public

ltejedor / vases

18 runs
Public

ltejedor / industrial-design

0 runs
Public