Model← Models
Qwen3.8-27B GSQ-RCO IQ3_S (ISTA-DASLab)
27B dense, IQ3_S (per-tensor gradient search), 11.3 GB.
- Parameters
- 27B
- Quant
- IQ3_S (per-tensor gradient search)
- Size
- 11.3 GB
- Family
- qwen3.8
qwen38-27b-gsq-rco-iq3s
Measured, not seateddenseresidentllama.cpp
Model card ↗Outcome as of 20 September 2026, from the seat registry. The write-up below was made when the model was tested.
Why it was tested
Same weights as qwen3.8-27b at ~3 bits instead of ~4.5, with the quantisation type chosen per tensor by gradient search under a size budget. Retains the MTP head. 26% fewer bytes per token and 8% faster.
What came of it
Lossless on four suites and not on the fifth. 202 of 212 cases identical to Q4_K_M; all ten changes in nullschema (76.4% to 62.5%). The vendor's task-lossless claim (AIME25 100.00, LiveCodeBench 85.71, GPQA within 0.51) appears honest - none of those benchmarks contains an absent-answer case. Use Q4_K_M for extraction; IQ3_S is fine for anything else.
No runs recorded against this identifier.