Downloads · 30 days
716
31% of all-time downloads
esatapedico/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-W4A16-T400
Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-W4A16-T400 is a text generation model from esatapedico. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
NVFP4 checkpoint of DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored, quantized for vLLM serving. NVFP4 here means W4A16 with FP8 scales, group size 16, weight only, 400 tensors. No calibration data w…
Downloads · 30 days
716
31% of all-time downloads
All-time downloads
2.3K
Public
Parameters
27.8B
40.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors20.6 GB · 100%
How the weights are stored.
U824.3B · 88%
From the Hugging Face model README
NVFP4 checkpoint of DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored, quantized for vLLM serving. NVFP4 here means W4A16 with FP8 scales, group size 16, weight only, 400 tensors. No calibration data was used.
HF repo: esatapedico/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4-W4A16-T400
| Field | Value |
|---|---|
| Format | compressed-tensors nvfp4-pack-quantized |
| Quantization | W4A16, group size 16, FP8 E4M3 scales, weight only, 400 NVFP4 tensors |
| Kept in BF16 | lm_head, vision tower, MTP head, DeltaNet conv1d and in_proj_a/b |
| Calibration | none |
| Base | DavidAU/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored (Qwen3.8-27B, Apache 2.0) |
Quantized set covers the MLP on all 64 layers, Q, K, V, O on the 16 full attention layers, the token embeddings, and the DeltaNet in_proj_qkv/z/out_proj tensors. The lm_head stays at full precision on purpose: vLLM runs the output head unquantized regardless, and no vLLM release loads a compressed-tensors NVFP4 head, so quantizing it only breaks serving with zero runtime gain. Vision tower, MTP head, and the DeltaNet conv1d plus in_proj_a/b dynamics stay at full precision following the JC1DA exception pattern.
Built for vLLM and engines consuming vLLM-compatible compressed-tensors checkpoints, following the JC1DA-style exception pattern. Verified serving: tensor parallel 2, 2048 context, 9 GB per GPU with ample KV headroom, coherent generation. Serve with --quantization compressed-tensors semantics (auto-detected from the config); FP8 KV remains a runtime flag, not checkpoint bytes. Keep vision intact and MTP for speculative decoding; no GGUF inside this repo.
model.safetensors about 19 GBconfig.json quantization_config.format=nvfp4-pack-quantized, quant_method=compressed-tensors, Qwen3_5ForCausalLM, 64 layers, hybrid GatedDeltaNet, 262144 context, MTP headtokenizer.json intact, chat template intactDerivative 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. Exception pattern follows the JC1DA INT4-W4A16 reference. A companion GGUF-parent checkpoint with the conservative 256-tensor recipe lives at esatapedico/Qwen3.8-27B-TWIN-TURBO-Fable-Cold-Fusion-709-L-Uncensored-NVFP4.
I post updates on new conversions, benchmarks, and what I'm working on over on my site. Follow along there to keep up with new releases and the work in progress. If you'd like to support more of it, you will find the options there. I do this on consumer hardware and like seeing how far it goes. More is on the way.
🌐 esatapedico.com. Updates, work-in-progress, and ways to support.
apache-2.0
Card written with AI assistance.