Update Modelfile-Pixtral-12B-Q8_0.md

Modelfile-Pixtral-12B-Q8_0.md

@@ -1,26 +1,33 @@
-# Pixtral-12B-GGUF Modelfile (Q2_K)
+# Pixtral-12B-GGUF Modelfile (Q8_0)
 # ---------------------------------
 # 
 # Tested with: Ollama v0.11.X-->v0.12.6(latest)
-# Quantization: Q2_K (Quant created by = ggml-org)
-# Quality: Decent/Okay - Recommend Q4_K_S or higher...
+# Quantization: Q8_0 (Quant created by = ggml-org)
+# Quality: Extremely-High-Quality (Updated 2025/10/28)
+# Real-world usability: Very Recommended!
 # ----------------------------------------------------
 # 
 # Vision Notes:
 # Some users may need to set the context value -or- "num_ctx"
-# value to at least ~12K-->19K.
+# value to ~9K-->19K.
+# Personally tested with: num_ctx=9982 and num_ctx=19982
 # -----------------------------------------------------------
 # 
 # Created by:
 # EnlistedGhost (aka Jon Zaretsky)
-# --------------------------------
+# Original GGUF by: https://huggingface.co/ggml-org
+# Original GGUF type: Static Quantize (non-iMatrix)
+# ----------------------------------------------------------
+# | Warning! - iMatrix Quantize seems to suffer in regards |
+# | to vision quality, but are still made available        |
+# ----------------------------------------------------------
 # 
 # Goal:
 # To provide the FIRST actually functional and usable
 # GGUF model version of the Mistral Pixtral-12B for
 # direct-usage with Ollama!
 # Currently, there are NO USABLE OR WORKING versions
-# of this model...
+# of this model that are usable with Ollama...
 # ---------------------------------------------------
 # 
 # Big/Giant/Huge Thank You: