geoffmunn
/

Qwen3-4B

Text Generation

Model card Files Files and versions

geoffmunn commited on Oct 7

Commit

e33dd7f

·

verified ·

1 Parent(s): ddf8f15

Quality & Performance updated

Files changed (1) hide show

Qwen3-4B-Q5_K_S/README.md +2 -3

Qwen3-4B-Q5_K_S/README.md CHANGED Viewed

@@ -14,7 +14,7 @@ base_model: Qwen/Qwen3-4B
 author: geoffmunn
 ---
-# Qwen3-4B-Q5_K_S
 Quantized version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) at **Q5_K_S** level, derived from **f16** base weights.
@@ -30,10 +30,9 @@ Quantized version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) at **
 | Metric | Value |
 |-------|-------|
-| **Quality** | High |
 | **Speed** | 🐢 Medium |
 | **RAM Required** | ~3.5 GB |
-| **Recommendation** | Great for reasoning; slightly faster than Q5_K_M. |
 ## Prompt Template (ChatML)

 author: geoffmunn
 ---
+# Qwen3-4B:Q5_K_S
 Quantized version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) at **Q5_K_S** level, derived from **f16** base weights.
 | Metric | Value |
 |-------|-------|
 | **Speed** | 🐢 Medium |
 | **RAM Required** | ~3.5 GB |
+| **Recommendation** | Did not appear in the top 3 for any question. Not recommended. |
 ## Prompt Template (ChatML)