Hugging Face's logo

vmlinux
/
Qwen3.8-27B-AEON-ULTIMATE-ROCmFPX-GGUF

Text Generation
GGUF
llama.cpp
rocm
rocmfpx
amd
strix-halo
qwen3.8
qwen35
imatrix
thinking
uncensored
Model card Files
xet
 Community
1
Qwen3.8-27B-AEON-ULTIMATE-ROCmFPX-GGUF / BUILD_RESULTS.md
vmlinux's picture
vmlinux
Add model card, iMatrix, and provenance
5f3b0aa verified
preview code
|
Raw History Blame Contribute Delete
1.26 kB

Build results

Artifact Preset Bytes BPW SHA-256
Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP4-iMatrix.gguf Q4_0_ROCMFP4 17,735,469,440 5.19 34c04aaec2399fab8179a921d0ea1e9d3b93da213201ab0ec2930ee1420307b0
Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP6-iMatrix.gguf Q6_0_ROCMFPX 22,528,383,360 6.59 d096fdd0ece150cefa793a8fdae55076b63d61d9e135571de6c73b016a641ba1
Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-ROCmFP8-iMatrix.gguf Q8_0_ROCMFPX 28,193,397,120 8.25 10eff5653c51e23a8a816761feea69b235c9003e80821759ecef41814843a761

Calibration

  • Source: Aeon BF16 checkpoint at revision 8f76e82ed7ef4de7735f5d4148fce7b643b00fae
  • Corpus: calibration.txt, SHA-256 9e793fe49eacd9e72ab7a472cf96196e6954ea4b75f312a2d50dd154dc14c1fc
  • Matrix: Qwen3.8-27B-AEON-ULTIMATE-iMatrix.imatrix.gguf
  • Matrix SHA-256: db55aea9f171b38dcdfdb1b56ffa57aca1fdbcef930b32539eb3d69e492e1f3b
  • Coverage: 339 chunks, 496 entries, 512-token chunks

Validation

  • BF16 conversion dry-run: passed, 866 tensors with bundled MTP.
  • iMatrix-aware quantizer dry-runs: passed for FP4, FP6, and FP8.
  • ROCm0 completion smoke: passed for all three quantizations with all layers offloaded.