Unverified50% confidenceFactExact time
There is currently no NVFP4 build of AREX-2; available quantized versions include BAAI's original BF16 (54.7 GB), prithivMLmods' FP8 (35.9 GB), cyankiwi's AWQ INT4 (20.2 GB), and numsu's INT4 W4A16 (18.6 GB).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/15/2026
First Seen
Valid until: 10/29/2026
Sources
Related Entities
Related Claims
Unverified开发者提供五种量化格式：INT8 ConvRot(4.5GB)、FP8 E4M3(4.2GB)、bf16(8.3GB)、NVFP4(2.9GB)、MXFP8(4.7GB)74% similarUnverifiedNVIDIA L4 (g6/SageMaker) natively supports bf16, fp8, and int8, and int4 is widened to 16 bits; NVIDIA T4G (g5g) supports bf16 (emulated) and int8, does not support fp8, and widens int4 to 16 bits; NeuronCore-v2 (inf2/trn1) supports bf16 and int8, fp8 has hardware support but the compiler has yet to catch up, and int4 is widened to bf16 and is 27 times slower per call.72% similarUnverifiedd1-omni-600M 各量化格式的磁盘占用：原始 F32 safetensors 2.35 GB，GGUF F16 约 1.2 GB，GGUF Q8_0 约 670 MB，ONNX q8（纯文本）0.41 GB，ONNX q4（纯文本）0.24 GB，ONNX 语音栈 0.67 GB。71% similarUnverifiedThe BF16 weight files for Naive-N0.5-Flash are approximately 618GB, and the FP8 format version weights are approximately 315GB70% similarUnverified32GB of VRAM can run FP16 and FP8 original models directly, without needing to use GGUF quantized versions.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1033436API
curl https://kongchang.com/api/v1/knowledge/claims/1033436MCP
get_claim(id=1033436)