Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
lued
/
Qwen3.8-27B-INT8-W8A16-MTP
like
68
Image-Text-to-Text
Safetensors
vllm
qwen3_5
qwen3.8
compressed-tensors
w8a16
int8
quantized
mtp
speculative-decoding
vision
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
5
Copy to bucket
new
main
Qwen3.8-27B-INT8-W8A16-MTP
31.6 GB
Ctrl+K
Ctrl+K
1 contributor
History:
7 commits
lued
Rebuild README with measured benchmarks and safe serving defaults
7c12373
verified
16 days ago
.gitattributes
Safe
1.57 kB
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
README.md
Safe
25.1 kB
Rebuild README with measured benchmarks and safe serving defaults
16 days ago
chat_template.jinja
Safe
9.99 kB
Adopt unsloth chat template: developer-role support, reasoning_effort high->xhigh remap, stricter tool-call validation
17 days ago
config.json
Safe
20.7 kB
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
generation_config.json
Safe
202 Bytes
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
model-00001-of-00006.safetensors
Safe
5.29 GB
xet
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
model-00002-of-00006.safetensors
Safe
5.33 GB
xet
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
model-00003-of-00006.safetensors
Safe
5.35 GB
xet
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
model-00004-of-00006.safetensors
Safe
5.37 GB
xet
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
model-00005-of-00006.safetensors
Safe
5.34 GB
xet
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
model-00006-of-00006.safetensors
Safe
4.09 GB
xet
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
model.safetensors.index.json
Safe
198 kB
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
model_mtp.safetensors
Safe
849 MB
xet
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
preprocessor_config.json
Safe
390 Bytes
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
recipe.yaml
Safe
269 Bytes
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
tokenizer.json
Safe
20 MB
xet
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
tokenizer_config.json
Safe
11.4 kB
Adopt unsloth chat template: developer-role support, reasoning_effort high->xhigh remap, stricter tool-call validation
17 days ago
video_preprocessor_config.json
Safe
385 Bytes
Qwen3.8-27B day-one W8A16 (INT8) + BF16 MTP, compressed-tensors pack-quantized
17 days ago
