gauravmm

GLM-4.5-Air-REAP-82B-A12B-NVFP4

Deploy Dedicated

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Model Details

Model Provider

gauravmm

Model Tree

Base

cerebras/GLM-4.5-Air-REAP-82B-A12B

Quantized

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: mit

Serving (vLLM)

bash

vllm serve gauravmm/GLM-4.5-Air-REAP-82B-A12B-NVFP4 \  --quantization compressed-tensors \  --moe-backend marlin \  --trust-remote-code \  --max-model-len 65536 \  --kv-cache-dtype fp8

--moe-backend marlin is mandatory on this NVFP4 W4A16 checkpoint — the flashinfer_cutlass MoE backend rejects W4A16 NVFP4 and crashes engine-core init.

Provenance

GLM-4.5-Air (zai-org, MIT) → REAP prune (Cerebras) → NVFP4 W4A16 (this repo). License inherited from upstream: MIT.