license: apache-2.0
base_model: DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored
pipeline_tag: text-generation
library_name: transformers
tags:
- nvfp4
- qwen3.8
- qwen3.5
- blackwell
- mtp
- speculative-decoding
- turbo
- twin-turbo
- fable
- cold-fusion
- compressed-tensors
language: - en
- multilingual
quantization_config:
quant_method: compressed-tensors
format: nvfp4-pack-quantized
Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4
NVFP4 checkpoint of DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored. NVFP4 here means W4A16 with FP8 scales, group size 16, weight only. Linear layers are NVFP4, vision tower, linear attention path, lm_head and MTP head are kept in BF16 at the source. No calibration data was used. This matches the pattern used for other Qwen3.8 Cold Fusion NVFP4 builds.
HF repo: esatapedico/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4
GGUF family: planned in esatapedico/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-GGUF (tier ladder over a shared NVFP4 backbone, see that repo card when live)
At a glance
| Field | Value |
|---|---|
| Format | compressed-tensors nvfp4-pack-quantized |
| Quantization | W4A16, group size 16, FP8 E4M3 scales, weight only |
| Kept in BF16 | vision tower, linear attention path, lm_head, embeddings, MTP head |
| Calibration | none |
| Base | DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored (Qwen3.8-27B, Apache 2.0) |
Quantized set covers MLP on all 64 layers plus Q, K, V, O on the 16 full attention layers (256 NVFP4 tensors verified). The DeltaNet path stays BF16 in this checkpoint and is normalized to NVFP4 in the GGUF tier builds (448 tensor backbone).
Checkpoint
- Single
model.safetensorsabout 25 GB config.jsonquantization_config.format=nvfp4-pack-quantized,quant_method=compressed-tensors,Qwen3_5ForCausalLM, 64 layers, hybrid GatedDeltaNet, 262144 context, MTP headtokenizer.jsonintact, chat template intact- NVFP4 tensors verified via metadata checks, plus a vLLM smoke check (tensor parallel 2, coherent generation) before the GGUF tier builds
Provenance
Derivative of DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored (Apache 2.0) which itself derives from Qwen/Qwen3.8-27B. The TWIN-TURBO tune targets reduced thinking tokens with matched output quality. See the GGUF model card for full attribution once published.
License
apache-2.0
Card written with AI assistance.