Hugging Face's logo

Fortytwo-Network
/
Strand-Rust-Coder-14B-v1

Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
Model card Files
xet
Community
inikitin commited on
Commit
e27ab31
·
verified ·
1 Parent(s): 24ff49f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -219,10 +219,10 @@ These builds are compatible with **llama.cpp**, **Jan**, **LM Studio**, **Ollama
219
 
220
  | **Quantization** | **Size** | **Bit Precision** | **Description** |
221
  |------------------|-----------|------------------|----------------|
222
- | **Q4_K_M** | 8.99 GB | **4-bit** | Ultra-fast, compact variant for consumer GPUs and laptops |
223
- | **Q5_K_M** | 10.5 GB | **5-bit** | Lightweight deployment with strong accuracy retention |
224
- | **Q6_K** | 12.1 GB | **6-bit** | Balanced performance and efficiency |
225
  | **Q8_0** | 15.7 GB | **8-bit** | Near-full precision, for most demanding local inference |
 
 
 
226
 
227
  Quant versions: [Fortytwo-Network/Strand-Rust-Coder-14B-v1-GGUF](https://huggingface.co/Fortytwo-Network/Strand-Rust-Coder-14B-v1-GGUF)
228
 
 
219
 
220
  | **Quantization** | **Size** | **Bit Precision** | **Description** |
221
  |------------------|-----------|------------------|----------------|
 
 
 
222
  | **Q8_0** | 15.7 GB | **8-bit** | Near-full precision, for most demanding local inference |
223
+ | **Q6_K** | 12.1 GB | **6-bit** | Balanced performance and efficiency |
224
+ | **Q5_K_M** | 10.5 GB | **5-bit** | Lightweight deployment with strong accuracy retention |
225
+ | **Q4_K_M** | 8.99 GB | **4-bit** | Ultra-fast, compact variant for consumer GPUs and laptops |
226
 
227
  Quant versions: [Fortytwo-Network/Strand-Rust-Coder-14B-v1-GGUF](https://huggingface.co/Fortytwo-Network/Strand-Rust-Coder-14B-v1-GGUF)
228