Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -4,11 +4,16 @@ license: apache-2.0
|
|
| 4 |
license_link: https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
base_model: Qwen/Qwen3-Coder-Next
|
|
|
|
| 7 |
datasets:
|
| 8 |
- nvidia/Llama-Nemotron-Post-Training-Dataset
|
| 9 |
language:
|
| 10 |
- en
|
| 11 |
- zh
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
tags:
|
| 13 |
- qwen
|
| 14 |
- qwen3
|
|
@@ -37,6 +42,8 @@ quantized_by: bullpoint
|
|
| 37 |
|
| 38 |
# Qwen3-Coder-Next-AWQ-4bit
|
| 39 |
|
|
|
|
|
|
|
| 40 |
## Highlights
|
| 41 |
|
| 42 |
This is a 4-bit AWQ quantized version of [**Qwen3-Coder-Next**](https://huggingface.co/Qwen/Qwen3-Coder-Next), an open-weight language model designed specifically for coding agents and local development. It features the following key enhancements:
|
|
|
|
| 4 |
license_link: https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
base_model: Qwen/Qwen3-Coder-Next
|
| 7 |
+
base_model_relation: quantized
|
| 8 |
datasets:
|
| 9 |
- nvidia/Llama-Nemotron-Post-Training-Dataset
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
- zh
|
| 13 |
+
model_name: Qwen3-Coder-Next-AWQ-4bit
|
| 14 |
+
model-index:
|
| 15 |
+
- name: Qwen3-Coder-Next-AWQ-4bit
|
| 16 |
+
results: []
|
| 17 |
tags:
|
| 18 |
- qwen
|
| 19 |
- qwen3
|
|
|
|
| 42 |
|
| 43 |
# Qwen3-Coder-Next-AWQ-4bit
|
| 44 |
|
| 45 |
+
> **Model Size:** 80B total parameters, 3B activated | **Quantization:** 4-bit AWQ | **VRAM:** ~45GB
|
| 46 |
+
|
| 47 |
## Highlights
|
| 48 |
|
| 49 |
This is a 4-bit AWQ quantized version of [**Qwen3-Coder-Next**](https://huggingface.co/Qwen/Qwen3-Coder-Next), an open-weight language model designed specifically for coding agents and local development. It features the following key enhancements:
|