This is the immutable trained-control comparator for the release family. It contains the reasoning QLoRA merge before Abliterix, allowing direct comparison and fallback without presenting the winner as universally dominant.

Comparator status: trained reasoning control, not the untouched upstream Qwen base and not an Abliterix model.

Why this release

The target was a practical personal reasoning/VLM model with much lower reflexive refusal while retaining measured capability and an immutable fallback. The benchmark table is the decision record: it shows where the selected winner improved, where the control stayed stronger, and why both are published. The family therefore describes the winner as a practical personal-model selection with measured deviations, not universal dominance.

What this variant is

Role: Full-precision baseline comparator
Format: Merged BF16 Transformers checkpoint with the native 15-tensor MTP sidecar preserved as mtp.safetensors.
Base: Qwen/Qwen3.8-27B
Pipeline: image + text to text
License: Apache-2.0

Frozen local results

These are self-run, frozen local project benchmarks, not official Qwen benchmarks. The same local harness compared control-bf16 with abliterix-pass1-bf16.

Frozen local metric	Control	Abliterix winner
Harmful hard refusal	43.2%	0.0%
Harmful soft deflection	14.6%	0.2%
Harmful substantive response	47.0%	99.4%
Capability macro	17.6859%	21.0086%
Full code	16/421	10/421
HumanEval	7.9268%	4.2683%
Long-form pass	54.1667%	62.5000%
MMMU30	9/30	11/30
Held-out loss ratio	1.000000	1.024478
Benign KL	0.000000	0.093614

The winner improved the local capability macro by 3.3227 points, long-form pass rate by 8.3333 points, and MMMU30 by 2 correct answers while reducing harmful hard refusal by 43.2 points. The control remained better on full code/HumanEval.

Full machine-readable values are in benchmark-results.json.

Strict deviations and code pathology

Benign KL was 0.093614, above the strict 0.05 limit.
Incoherence was 4.3077%, above the 2.7692% strict comparison point.
HumanEval was 4.2683% versus control 7.9268%; full code was 10/421 versus 16/421.
Long-form maximum repeated-4gram fraction was 5.8632%, above the 5% limit.
Prompt leakage was detected: 3 exact winner prompt echoes versus 2 for control; both failed the leakage hard gate.
376/421 winner code generations hit the 512-token cap. Among generations that reached execution, the winner passed 10/46 (21.74%) versus control 16/103 (15.53%), pointing to severe termination/extraction pathology rather than a clean latent-code estimate.

Training data and run

Aggregate source label	Rows
`opus-10000x`	9,633
`opus-3000x`	2,326
`reasoning-700x`	633
`high-reasoning-250x`	250
Raw total	12,842

After 208 deduplications and 20 invalid-row removals, 12,614 rows remained: 12,349 train, 127 validation, and 138 test. The processed-manifest SHA-256 is 6e0a36ad20732c5f98ff592c4565a4c86876fead4e9f94bc6ceedfad1339a94d. Only aggregate counts and hashes are published; raw/private rows are not.

Training ran for 1,544 optimizer steps with 108,789,760 trainable LoRA parameters. Final validation loss was 0.23739749; token accuracy was 91.7594%.

Architecture and lineage

The model uses Qwen3_5ForConditionalGeneration as recorded by the released config: a 64-layer, hidden-size-5120 text stack with a 3:1 linear/full-attention schedule and a configured 262,144-token maximum position range, paired with a 27-layer, hidden-size-1152 vision encoder. It is an image/text conditional-generation model, not a text-only checkpoint.

Method

Started from Qwen/Qwen3.8-27B, Apache-2.0.
Prepared 12,842 raw reasoning rows: 12,614 accepted after removing 208 duplicates and 20 invalid rows, then split into 12,349 train / 127 validation / 138 test rows.
Trained a reasoning QLoRA on the 12,349-row train split for 1,544 optimizer steps with 108,789,760 trainable LoRA parameters. Final validation loss was 0.23739749 and token accuracy was 91.7594%.
Merged the adapter to BF16 to form immutable control-bf16.
Produced the selected winner with Abliterix 1.12.2 pass 1 (seed 42): orthogonal/projected, winsorized single-direction residual steering over the output/down-projection writer components. Q/K/V projections were excluded.
Preserved BF16 releases and converted both variants to affine MLX 8-bit, group size 64. Native one-layer MTP drafters were split and validated separately.

The final selection label is selected_practical_winner_with_measured_deviations. Private training data, raw harmful/benign prompt sets, operational receipts, local paths, and Drive metadata are intentionally not published.

Tensor and conversion integrity

The merged control retained all 1,199 tensor keys, including 15 native MTP tensors and 333 vision tensors. It received no Abliterix residual-writer edits.

MLX native proof ran through mlx-vlm on arm64 macOS/Metal. Ordinary and MTP-assisted generation both produced the exact answer 323 for winner and control. The winner MLX build used mlx 0.32.0, mlx-lm 0.31.3, mlx-vlm 0.6.13, and affine 8-bit group-64 quantization.

Hash and size summary

BF16 trained control: 21 files, 55,583,127,863 bytes, sealed aggregate SHA-256 51979419f5f2fa5860f3cf9b9cd1c54d8e4e8f1585e5a182dea395e3ef3e11e9

The deliberately published model payload for this repository is 20 files / 55,583,123,681 bytes. Per-file source SHA-256 values are in SHA256SUMS and manifests/artifact-manifest.json. Sealed aggregate hashes above cover the complete local source components, including private entries excluded from publication; use the per-file public manifest for the Hub payload.

Use with Transformers

A current Transformers version that supports Qwen3.8/Qwen3.5 VLM architecture is required (the sealed build used 5.15.0). BF16 needs substantial accelerator memory.

python

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

repo_id = "timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16"
processor = AutoProcessor.from_pretrained(repo_id)
model = AutoModelForImageTextToText.from_pretrained(
    repo_id, torch_dtype=torch.bfloat16, device_map="auto"
)
messages = [{"role": "user", "content": [
    {"type": "text", "text": "Calculate 17 multiplied by 19."}
]}]
inputs = processor.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True,
    return_dict=True, return_tensors="pt"
).to(model.device)
output = model.generate(**inputs, max_new_tokens=256)
trimmed = output[:, inputs.input_ids.shape[1]:]
print(processor.batch_decode(trimmed, skip_special_tokens=True)[0])

For image input, add an image content item using the upstream Qwen multimodal message format. mtp.safetensors is the preserved native MTP sidecar; ordinary Transformers loading does not require it.

Known limitations

The control retained much more refusal behavior (43.2% hard refusal on the frozen harmful suite) and scored below the winner on capability macro, long-form, and MMMU30.
It is a project comparator, not an official Qwen baseline result.
BF16 is large and requires substantial memory; MTP support depends on the runtime.
The local benchmark suite and private training/evaluation data are not included. Results may not transfer to other prompts, languages, runtimes, or sampling settings.
Generated content can be incorrect, insecure, or incomplete; review it before consequential use.

Release family

See RELEASE_FAMILY.md for the role and integrity summary of every variant.

Responsible use

Evaluate this model for your own setting, isolate untrusted code/tool output, and comply with applicable law and the policies of systems you connect it to. The uncensoring/abliteration work changes refusal behavior; it does not make outputs accurate or safe by default.

License and attribution

Released under Apache License 2.0. This is a derivative of Qwen/Qwen3.8-27B, Copyright 2026 Alibaba Cloud. Qwen/Alibaba Cloud attribution and the full license text are retained in LICENSE. Modifications include the personal reasoning QLoRA merge, selected Abliterix residual edits for winner variants, and MLX quantization where applicable.

Support

If this release is useful, follow timteh673, star the repository, and share reproducible benchmark or runtime findings in the Hub community tab.