Home › Evidence › Records › cfg-0001

cfg-0001

backfilled
citable URL: https://halobench.com/records/cfg-0001/ — this address never moves; the anchor /records/#cfg-0001 keeps resolving
modelunsloth/Qwen3.6-35B-A3B-GGUF · UD-Q4_K_XL
engineggml-org/llama.cpp unknown-2026-06 · rocm · host aibeast (igpu)
flags-ngl 999 --no-mmap --parallel 1 -fa 1 --jinja -c 131072 (reasoning OFF / enable_thinking:false; q8_0 KV; no MTP — this GGUF ships no heads)
templatenot recorded at test time
treeupstream — stock
aged evidence — reconstructed from the archive. llama.cpp commit, chat-template hash and the memory block were not recorded at test time. Quant, backend, context, KV quant, serving flags and the reasoning setting are from the Phase 3C write-up.

Capability basis

unmeasured — performance numbers on this config stand on a guard alone, not an established capability

production node(s): qwen36-35b-a3b

Runs on this config (3)

rundatekindsuitemetrics
run-00012026-06-27performancetool-loop@v2.1decode_tps=69 · prefill_tps=354 · ttft_ms=180
run-00032026-06-28capabilityconceptual-c1-c8-blind@v1time_to_correct_answer_s=1.7
run-00042026-06-27guardtool-loop@v2.1tool_call_success=0.94 · turns_before_degradation=10+ · empty_arg_calls=0