Downloads · 30 days
376
80% of all-time downloads
Qwen3.8-27B-Heretic-FP8
darrellbest/Qwen3.8-27B-Heretic-FP8
Qwen3.8-27B-Heretic-FP8 is a image-text-to-text model from darrellbest. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
FP8 (W8A8, dynamic activation scales) build of darrellbest/Qwen3.8-27B-Heretic, for vLLM. 35 GB instead of 51 GB.
All-time downloads
470
Public
Parameters
27.4B
36.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors36.8 GB · 100%
Parameter types
How the weights are stored.
F8_E4M318.8B · 68%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B Heretic FP8
FP8 (W8A8, dynamic activation scales) build of darrellbest/Qwen3.8-27B-Heretic, for vLLM. 35 GB instead of 51 GB.
What is quantized
| Part | Precision |
|---|---|
| Linear layers of the MLPs and attention | FP8 (float8_e4m3fn, dynamic per-token activation scales) |
Gated DeltaNet (linear_attn) layers, vision tower, embeddings, lm_head, MTP | bf16 (unchanged) |
The linear-attention layers carry a recurrent state and the vision tower encodes images; both stay in bf16, as in
the FP8 builds of related models. Multi-token-prediction weights are preserved in model-auxiliary.safetensors
(save_pretrained drops them for this architecture).
Made with llm-compressor 0.13.0, FP8_DYNAMIC, which needs no
calibration data.
Use
vllm serve darrellbest/Qwen3.8-27B-Heretic-FP8
Ablation
0/100 refusals against 98/100 for the original, KL divergence 0.0465. Method and parameters are on the parent card. The FP8 weights themselves were not re-measured; the figures are the parent model's.
Reduced safety guardrails by design. You are responsible for what you do with it.
The family
| Repository | Format | Size | Use it with |
|---|---|---|---|
| Qwen3.8-27B-Heretic | bf16 safetensors | 51 GB | transformers, vLLM, SGLang |
| Qwen3.8-27B-Heretic-GGUF | GGUF BF16 / Q8_0 / Q4_K_M (+ vision) | 51 / 27 / 16 GB | llama.cpp, Ollama |
| Qwen3.8-27B-Heretic-FP8 | FP8 W8A8, compressed-tensors | 35 GB | vLLM |
| Qwen3.8-27B-Heretic-NVFP4 | NVFP4, compressed-tensors | 27 GB | vLLM on Blackwell |
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Sep 24, 2026
- Updated
- Sep 24, 2026