Hugging Face's logo

dougiefresh
/
jade_qwen3_4b_mlx_4bit

Text Generation
MLX
Safetensors
Rust
English
qwen3
grammar
logic
rhetoric
math
programming
aarch64
c
nushell
conversational
4-bit precision
Model card Files
xet
 Community
dougiefresh commited on
Commit
67881ff
·
verified ·
1 Parent(s): d5882ff

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -2
README.md CHANGED
@@ -4,10 +4,13 @@ datasets:
4
  - dougiefresh/grammar_logic_rhetoric_and_math
5
  - dougiefresh/systems_programming_and_administration
6
  - dougiefresh/systems_programming_code_conversations
 
7
  language:
8
  - en
9
- base_model: dougiefresh/jade_qwen_4b
 
10
  tags:
 
11
  - logic
12
  - rhetoric
13
  - math
@@ -16,8 +19,17 @@ tags:
16
  - c
17
  - rust
18
  - nushell
19
- - grammar
20
  - mlx
21
  library_name: mlx
22
  pipeline_tag: text-generation
23
  ---
 
 
 
 
 
 
 
 
 
 
 
4
  - dougiefresh/grammar_logic_rhetoric_and_math
5
  - dougiefresh/systems_programming_and_administration
6
  - dougiefresh/systems_programming_code_conversations
7
+ - dougiefresh/jade_identity
8
  language:
9
  - en
10
+ base_model:
11
+ - Qwen/Qwen3-4B
12
  tags:
13
+ - grammar
14
  - logic
15
  - rhetoric
16
  - math
 
19
  - c
20
  - rust
21
  - nushell
 
22
  - mlx
23
  library_name: mlx
24
  pipeline_tag: text-generation
25
  ---
26
+
27
+ # Jade Qwen 3 4B - 4bit quantization for MLX
28
+
29
+ A systems progamming Qwen finetune.
30
+
31
+ ![Jade](./Jade.jpeg)
32
+
33
+ ## Model description
34
+
35
+ Please view the model [description on the non-quantized version](https://huggingface.co/dougiefresh/jade_qwen3_4b).