Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-FP8-Dynamic

Uniform FP8 quantized version of Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled — a Claude 4.6 Opus reasoning-distilled Qwen3.5-27B model.

~29 GB on disk (~27 GiB in VRAM). Near-lossless FP8 quantization with only 1.4% perplexity degradation vs BF16. Recommended GPU: NVIDIA RTX PRO 6000 (96 GB) or other GPUs with >= 48 GB VRAM.

For 32 GB GPUs (RTX 5090): Use the NVFP4 mixed-precision variant instead (~25 GB, fits with usable context on a single 5090).

Quantization Strategy

Uniform FP8 W8A8 dynamic quantization using llm-compressor v0.10.1, stored in the compressed-tensors format. No calibration data needed — weight scales are computed statically per-channel, activation scales are computed dynamically per-token at inference time.

Weight Breakdown

Architecture

Qwen3.5-27B uses a hybrid DeltaNet + softmax attention architecture with full_attention_interval=4:

Layer pattern (64 layers):
  [DeltaNet, DeltaNet, DeltaNet, Softmax] × 16
  = 48 DeltaNet layers + 16 softmax attention layers

Key architectural parameters:

• Hidden size: 5,120
• Attention heads: 24 (query), 4 (KV, GQA)
• Head dimension: 256
• DeltaNet heads: 16 key, 48 value (dim 128 each)
• MLP intermediate: 17,408
• Vocabulary: 248,320
• Max position embeddings: 262,144

Only 16 of 64 layers require KV cache — the 48 DeltaNet layers use a fixed-size recurrent state that doesn't grow with sequence length. This gives ~4x more context capacity than a standard transformer of the same size.

KV Cache Budget

Per-token KV cache cost (only 16 softmax layers):

• FP16: 4 KV heads x 256 dim x 2 (K+V) x 2 bytes x 16 layers = 64 KB/token
• FP8: 32 KB/token

Usage

Serving with vLLM (recommended)

pip install vllm>=0.17.0

vllm serve mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-FP8-Dynamic \
  --max-model-len 131072 \
  --reasoning-parser qwen3

RTX PRO 6000 / high-VRAM GPUs (>= 48 GB):

vllm serve mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-FP8-Dynamic \
  --max-model-len 262144 \
  --reasoning-parser qwen3

Note: On RTX 5090 (32 GB), the same Blackwell-specific vLLM issues that affect the NVFP4 variant also apply here. See the NVFP4 model card for details and tracking PRs. On GPUs with >= 48 GB VRAM, these issues are irrelevant.

Transformers (direct loading)

from transformers import AutoTokenizer, Qwen3_5ForConditionalGeneration
import torch

model = Qwen3_5ForConditionalGeneration.from_pretrained(
    "mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-FP8-Dynamic",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "mconcat/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-FP8-Dynamic",
    trust_remote_code=True,
)

Compatibility

Hardware Requirements

Benchmark Results

Comparison against the BF16 source model. All benchmarks run on NVIDIA RTX PRO 6000 (96 GB) with vLLM 0.17.0, temperature=0.6 for generation tasks (Qwen recommended setting for thinking mode).

*FP8 MMLU-Pro and ARC ran with 50 samples (quick mode); BF16 used full sample sizes. Full FP8 benchmarks will be updated.

Summary: FP8 quantization is near-lossless — perplexity degrades only 1.4% vs BF16, while throughput improves 1.6x from reduced memory bandwidth. For comparison, the NVFP4 variant (25 GB) shows 2.1% perplexity degradation but fits in 4 GB less VRAM.

Source Model

This is a quantization of Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled, which is an SFT fine-tune of Qwen/Qwen3.5-27B using Claude 4.6 Opus reasoning distillation data.

Training datasets:

• nohurry/Opus-4.6-Reasoning-3000x-filtered
• TeichAI/claude-4.5-opus-high-reasoning-250x
• Jackrong/Qwen3.5-reasoning-700x

Quantization Details

• Tool: llm-compressor v0.10.1
• Format: compressed-tensors (uniform FP8)
• Scheme: FP8 W8A8 dynamic — per-channel static weight scales, per-token dynamic activation scales
• Calibration: None required (weight-only scale computation)
• Hardware: NVIDIA RTX PRO 6000 Blackwell (96 GB)

License

Apache 2.0, following the base model license.