Hourly Usage
Performance Metrics
Median Total Time
2.16s
Median TTFT
2.08s
Median Prefill TPS
15109.16
Median Gen TPS
21.65
Model Information
Context Size
262144
Quantization
r128 on INT8
Engine
vllm
Creation Method
Unknown
Model Type
Qwen38B
Chat Template
Qwen3.5
Reasoning
Yes
Vision
Yes
Parameters
27B
Added At
9/28/2026
base_model:
- Qwen/Qwen3.8-27B
- TeichAI/Qwen3.8-27B-Fable-Distill
- beyoru/Kiwen1.1-27B
- nlpguy/Qwen3.8-27B-Fimi-4 library_name: transformers tags:
- mergekit
- merge
merged
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Karcher Mean merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
chat_template: qwen
dtype: bfloat16
merge_method: karcher
modules:
default:
slices:
- sources:
- layer_range: [0, 0]
model: nlpguy/Qwen3.8-27B-Fimi-4
- layer_range: [0, 0]
model: beyoru/Kiwen1.1-27B
- layer_range: [0, 0]
model: Qwen/Qwen3.8-27B
- layer_range: [0, 0]
model: TeichAI/Qwen3.8-27B-Fable-Distill
model.language_model.layers:
slices:
- sources:
- layer_range: [0, 64]
model: nlpguy/Qwen3.8-27B-Fimi-4
- layer_range: [0, 64]
model: beyoru/Kiwen1.1-27B
- layer_range: [0, 64]
model: Qwen/Qwen3.8-27B
- layer_range: [0, 64]
model: TeichAI/Qwen3.8-27B-Fable-Distill
model.visual.blocks:
slices:
- sources:
- layer_range: [0, 27]
model: nlpguy/Qwen3.8-27B-Fimi-4
- layer_range: [0, 27]
model: beyoru/Kiwen1.1-27B
- layer_range: [0, 27]
model: Qwen/Qwen3.8-27B
- layer_range: [0, 27]
model: TeichAI/Qwen3.8-27B-Fable-Distill
out_dtype: bfloat16