Downloads · 30 days
319
14% of all-time downloads
Qwen3.8-27B-W8A8-INT8
compute1/Qwen3.8-27B-W8A8-INT8
Qwen3.8-27B-W8A8-INT8 is a text generation model from compute1. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Quantized from Qwen/Qwen3.8-27B using llm-compressor.
All-time downloads
2.3K
Public
Parameters
26.9B
31.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors31.2 GB · 100%
Parameter types
How the weights are stored.
I824.3B · 88%
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B W8A8 INT8 (compressed-tensors)
Quantized from Qwen/Qwen3.8-27B using llm-compressor.
Quantization Config
- Format:
int-quantized(compressed-tensors) - Weights: INT8, channel-wise, symmetric, MSE observer
- Activations: INT8, token-wise, symmetric, dynamic
- Ignored:
lm_head, embeddings, vision encoder, MTP layers, GDN linear-attn sub-modules (in_proj_a,in_proj_b,conv1d,norm,A_log,dt_bias), all layernorms, q_norm, k_norm
Architecture
Qwen3.8-27B uses a hybrid architecture with 48 Gated DeltaNet (GDN) linear-attention layers and 16 full-attention layers (every 4th layer). The GDN in_proj_a/in_proj_b projections are kept in BF16 because they require special handling for fused loading.
Intended Use
Optimized for inference on Ampere GPUs (RTX 3090, A100) with SGLang/vLLM Marlin kernels. Weight-only INT8 with BF16 activations.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_5_text
- License
- other
- Languages
- multilingual
- Created
- Aug 19, 2026
- Updated
- Aug 19, 2026