GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
philbert440
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
philbert440
Model Tree
philbert440/Qwen3.6-40B-DeckardUncensored-OpusDistilled-W4A16-AWQ
Input Modalities
Output Modalities
Supported Functionality
W4A16-AWQ — 4-bit weight-only (AWQ, compressed-tensors), FP16 activations. Runs on 1Cat-vLLM's SM70 TurboMind path (Tesla V100) and on stock vLLM (Ampere+).
Base model: philbert440/Qwen3.6-40B-DeckardUncensored-OpusDistilled-W4A16-AWQ
bash
# 1Cat-vLLM on 2x Tesla V100 (SM70): W4A16-AWQ + MTP. (Also runs on stock vLLM, Ampere+.)export VLLM_SM70_FLASH_ATTN_V100=1 VLLM_SM70_QUANT_BACKEND=turbomindpython -m vllm.entrypoints.openai.api_server \--model philbert440/Qwen3.6-40B-DeckardUncensored-OpusDistilled-HermesCalibrated-W4A16-AWQ --trust-remote-code --dtype half \--attention-backend FLASH_ATTN_V100 --tensor-parallel-size 2 \--kv-cache-dtype fp8_e5m2 --max-num-seqs 6 \--speculative-config '{"method":"mtp","num_speculative_tokens":4,"attention_backend":"FLASH_ATTN_V100","draft_sample_method":"greedy"}' \--compilation-config '{"cudagraph_mode":"full_and_piecewise","cudagraph_capture_sizes":[1,2,4,8]}'
See the Deckard-40B Uncensored collection for all tiers and formats (BF16 / W4A16-AWQ / NVFP4).
Abliteration removes safety refusals; you are responsible for lawful, ethical use.