bullpoint commited on
Commit
b035ac1
·
verified ·
1 Parent(s): 0111393

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +7 -0
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: