This GGUF will not run correctly with stock llama.cpp. You need the pinned ciru-ai/ROCmFPX runner because this file uses ROCmFP4 tensor types and MTP runtime paths that upstream llama.cpp does not currently understand.
The model file is provided here. You do not need to rebuild or quantize the model.
This is an uncensored local-assistant build. It is intended for users who explicitly want that behavior on their own hardware.
Why This Build
This build is for Strix Halo owners who want the uncensored HauhauCS Qwen3.6 35B-A3B behavior, but with the local serving speed and coding strength that CHADROCK/ROCmFP4 and MTP can unlock on AMD unified-memory hardware.
a 157/164 HumanEval base result with fast HumanEval generation
Technical Metadata
Hugging Face may round the parsed GGUF tensor count to 36B in its automatic badge. This release is the Qwen3.6 35B-A3B MoE family: about 35B-class total parameters with roughly 3B active parameters per token.
All local numbers below were measured on AMD Ryzen AI Max+ 395 / Strix Halo with the public MTP profile.
HumanEval
Model / row
HumanEval base
HumanEval+
CHADROCK3.6 35B Uncensored Strix Lean MTP
157/164 = 95.73%
150/164 = 91.46%
This is a strong HumanEval result for a local uncensored ROCmFP4/MTP GGUF run.
HumanEval Speed
Metric
CHADROCK3.6 35B Uncensored MTP
HumanEval tasks
164
total tokens processed
75,223
completion tokens generated
46,360
codegen wall time
488.0s
cumulative request latency
484.95s
mean request latency
2.96s
total-token throughput, prompt + completion
154.15 tok/s
completion-token generation throughput
95.60 tok/s
median per-request completion-token speed
95.21 tok/s
The total-token number counts prompt plus completion tokens over the full codegen wall time. The completion-token number counts generated completion tokens over request latency. The same EvalPlus HumanEval run produced the score table above and generated the full 164-task workload in about eight minutes of codegen wall time.
Best Settings / Advanced Setup
For the pinned runner build, copy-paste build commands, request-level speculative controls, and the 35B/27B reproduction notes, use the advanced Ciru setup page:
Use --parallel 1 for this MTP profile. One slot is part of the intended MTP serving setup.
Text Only
This release is served as text-only. The public Strix Lean profile uses --no-mmproj.
The upstream HauhauCS repo includes multimodal metadata and a matching projector exists locally, but the June 4, 2026 Ciru real-image gate failed for this model with MTP on and with MTP off. The clean non-MTP Hauhau ROCmFP4 path and the original Hauhau Q8 path also failed that gate. Because of that, this release does not advertise or recommend vision use.
Build The Required llama.cpp
The GGUF is already provided. You only need to build the custom llama.cpp server once:
Charlie12345, also known as @Italianclownz, added the ROCmFP4 llama.cpp path this GGUF needs. The method adds custom ROCmFP4 GGUF tensor types and AMD-focused backend support so Strix Halo systems can run these very compact high-throughput builds.
This is an experimental AMD ROCmFP4/MTP build. Performance depends on driver version, clocks, prompt shape, MTP acceptance, and serving flags. The numbers above are local reproducible measurements on Strix Halo, not universal llama.cpp claims.
