ThakiCloud

Qwen3.8-27B-Human-KO-Safety-NVFP4

README

License: apache-2.0

What was re-measured for this version (2026-09-07, temperature 0, thinking off, same serving config as bf16)

Quantization changes abstention behavior. So instead of copying over the bf16 card's figures, we re-measured them on this checkpoint.

Table with columns: Axis, bf16 original, This model (NVFP4), How to read it
Axis	bf16 original	This model (NVFP4)	How to read it
KoBBQ ambiguous-context abstention (8,139)	92.8%	89.5%	3.3pp lower. Misses the pre-registered target of 93%, +23.8pp over EXAONE 4.5's 65.7%
Change in disambiguated-context accuracy (vs. base 90.66)	−2.1pp	−0.9pp	Less over-abstention (within the −3pp threshold)
Conditional bias (among answered items)	0.861	0.848	Both miss the pre-registered target of 0.60 (structural — see the bf16 card)
Identity probe (8-language holdout, n=240)	96.2%	95.8%	1-item difference
MMLU English 1,000 (thinking off)	80.9%	80.0%	Within detection limit
Thinking-mode empty responses (100)	0	0	No format defect
Korean human-likeness pairwise win rate (n=175)	+14.3pp	+10.3pp	Judge uncalibrated, direction only
HumanEval (executed, same run, n=148)	97.1%	94.6%	−2.5pp, 4-item difference, within detection limit
KMMLU 1,000 (same run)	52.3%	54.4%	+2.1pp
Instruction following 100 (deterministic checker)	79%	81%	Equivalent

In one line: it abstains slightly less and also over-abstains slightly less — behavior similar to shifting β a bit toward 0.2. If abstention rate is the top priority, use bf16 or W4A16; if memory and speed on Blackwell come first, use this version. Capability gates (coding·KMMLU·instruction) were re-measured in the same run with bf16 as the reference arm and entered into the table above. The difference from the bf16 card's absolute values is because the runs differ; read the comparison only within the same run.

Quantization recipe

llm-compressor 0.13.0 GPTQ · calibration 1,024 samples × 2,048 tokens (chat format, 25% Korean) · dampening 0.01 · actorder static · scheme NVFP4 (MLP) + FP8_DYNAMIC (attention) · ignore: vision/visual, lm_head, embed_tokens, linear_attn.in_proj_a/b. Took 46 minutes (1x B200). Metadata is in quantize_meta.json; the actual group and ignore lists are in config.json's quantization_config, verbatim.

Serving

Blackwell (SM100+: B200·GB200·RTX 50) only. There is no NVFP4 kernel on Hopper or below.

bash
vllm serve ThakiCloud/Qwen3.8-27B-Human-KO-Safety-NVFP4 \
  --max-model-len 32768 --kv-cache-dtype fp8 --enable-prefix-caching

vLLM ≥ 0.28 auto-detects the scheme from config.json, so there is no need to pass --quantization separately. DFlash drafter speculative decoding is not recommended on NVFP4, since a single-stream penalty (0.71-0.82x) has been measured.

Limitations

The safety axis was measured with KoBBQ alone, and the table above is from a single build of this quantized checkpoint. Given the noise between requantization builds (our measured GSM8K figure is 3.56pp), a difference within 3pp is not attributed to the treatment.
The abstention rate of 89.5% differs from the bf16 card's 92.8%. Do not cite the bf16 figure for this model.
Other limitations and data provenance are the same as the bf16 card and DATA_PROVENANCE.md.

License

Apache-2.0 (same as Qwen/Qwen3.8-27B). See LICENSE · NOTICE.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

ThakiCloud

Model Tree

Base

ThakiCloud/Qwen3.8-27B-Human-KO-Safety

Quantized

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality