Massive MoE models ≥100B quantized with HLWQ · consumer deploy via vLLM expert offload
caio vicentino PRO
caiovicentino1
AI & ML interests
None yet
Recent Activity
updated a dataset about 6 hours ago
caiovicentino1/openinterp-multiprobe-dpo-poc published a dataset about 6 hours ago
caiovicentino1/openinterp-multiprobe-dpo-poc updated a dataset about 7 hours ago
caiovicentino1/ReasoningGuard-linearprobe-qwen36-27bOrganizations
None yet
HLWQ Models
Hadamard-Lloyd Weight Quantization · arXiv:2603.29078 · formerly PolarQuant
-
caiovicentino1/Qwen3.5-9B-HLWQ-Q5
Text Generation • 9B • Updated • 1.94k • 3 -
caiovicentino1/Qwen3.5-9B-HLWQ-MLX-4bit
Text Generation • 1B • Updated • 3.11k • 3 -
caiovicentino1/Qwen3.5-27B-HLWQ-Q5
Text Generation • 27B • Updated • 4.46k • 11 -
caiovicentino1/Qwen3.5-9B-HLWQ-Engine-v4
Text Generation • 7B • Updated • 538
HLWQ Large MoE (100B+)
Massive MoE models ≥100B quantized with HLWQ · consumer deploy via vLLM expert offload
HLWQ Models
Hadamard-Lloyd Weight Quantization · arXiv:2603.29078 · formerly PolarQuant
-
caiovicentino1/Qwen3.5-9B-HLWQ-Q5
Text Generation • 9B • Updated • 1.94k • 3 -
caiovicentino1/Qwen3.5-9B-HLWQ-MLX-4bit
Text Generation • 1B • Updated • 3.11k • 3 -
caiovicentino1/Qwen3.5-27B-HLWQ-Q5
Text Generation • 27B • Updated • 4.46k • 11 -
caiovicentino1/Qwen3.5-9B-HLWQ-Engine-v4
Text Generation • 7B • Updated • 538
spaces 15
pinned
Running on Zero
Agents
FabricationGuard Live Demo
🛡
Real-time fabrication detection on Qwen3.6-27B
pinned
Running
Agents
Qwen3.6 SAE Demo
🔬
Live token-level SAE feature for Qwen3.6-27B (AUROC 0.84)
pinned
Configuration error
OpenInterp
🔬
Watch language models think. Open source interpretability.
pinned
Paused
Agents
PolarQuant OmniWeaving Video
🧊
pinned
Paused
Agents
PolarQuant Demo
🧊
Configuration error
Agents
Qwen3.5-9B-Neo PolarQuant
🧊
models 63
caiovicentino1/qwen3.5-4b-crosscoder-rl-diff-papergrade
Updated
caiovicentino1/gemma2-2b-crosscoder-model-diff-papergrade
Updated
caiovicentino1/qwen36-27b-sae-papergrade
Updated
caiovicentino1/qwen36-27b-sae-multilayer
Text Generation • Updated
caiovicentino1/qwen36-feature-circuits
Updated
caiovicentino1/qwen36-crest-cognitive-heads
Updated
caiovicentino1/qwen35-a3b-sae-phase2
Updated
caiovicentino1/Huihui-Qwopus3.5-27B-v3-abliterated-HLWQ-Q5
Text Generation • 26B • Updated • 3.12k • 14
caiovicentino1/Qwen3.5-4B-SAE-L18-topk
Feature Extraction • Updated • 1
caiovicentino1/Qwen3.5-4B-mechreward-G3-phaseA-step400
Text Generation • Updated • 89
datasets 7
caiovicentino1/openinterp-multiprobe-dpo-poc
Updated
caiovicentino1/ReasoningGuard-linearprobe-qwen36-27b
Updated
caiovicentino1/openinterp-32-reasoningguard-rollouts
Updated
caiovicentino1/FabricationGuard-linearprobe-qwen36-27b
Viewer • Updated • 6 • 8
caiovicentino1/qwen35-a3b-thinking-traces
Viewer • Updated • 41.3k • 32
caiovicentino1/Qwen3.6-35B-A3B-mcr-stage-b
Viewer • Updated • 1 • 119 • 1
caiovicentino1/processflow
Updated • 89 • 1