Hugging Face's logo

kaitchup
/
Olmo-3-7B-Think-w8a8-smoothquant

Safetensors
olmo3
llmcompressor
8-bit precision
compressed-tensors
Model card Files
xet
Community
bnjmnmarie commited on
Commit
0945f00
·
verified ·
1 Parent(s): 71e0eee

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -7,6 +7,11 @@ tags:
7
  ---
8
  This is [allenai/Olmo-3-7B-Think](https://huggingface.co/allenai/Olmo-3-7B-Think) quantized with [LLM Compressor](https://github.com/vllm-project/llm-compressor) with Smoothquant (W8A8). The model is compatible with vLLM (tested: v0.11.2). Tested with an RTX 4090.
9
 
 
 
 
 
 
10
 
11
  - **Developed by:** [The Kaitchup](https://kaitchup.substack.com/)
12
  - **License:** Apache 2.0 license
 
7
  ---
8
  This is [allenai/Olmo-3-7B-Think](https://huggingface.co/allenai/Olmo-3-7B-Think) quantized with [LLM Compressor](https://github.com/vllm-project/llm-compressor) with Smoothquant (W8A8). The model is compatible with vLLM (tested: v0.11.2). Tested with an RTX 4090.
9
 
10
+ How the models perform (token efficiency, accuracy per domain, ...) and how to use them:
11
+ [Quantizing Olmo 3: Most Efficient and Accurate Formats](https://kaitchup.substack.com/p/quantizing-olmo-3-most-efficient)
12
+
13
+ ![image](https://cdn-uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/H3JWV_ha07IrN-Sz6C7VL.png)
14
+
15
 
16
  - **Developed by:** [The Kaitchup](https://kaitchup.substack.com/)
17
  - **License:** Apache 2.0 license