Update Modelfile-Pixtral-12B-Q2_K.md
Browse files
Modelfile-Pixtral-12B-Q2_K.md
CHANGED
|
@@ -3,8 +3,9 @@
|
|
| 3 |
#
|
| 4 |
# Tested with: Ollama v0.11.X-->v0.12.6(latest)
|
| 5 |
# Quantization: Q2_K (Quant created by = ggml-org)
|
| 6 |
-
# Quality: Good (Updated 2025/10/28)
|
| 7 |
-
#
|
|
|
|
| 8 |
#
|
| 9 |
# Vision Notes:
|
| 10 |
# Some users may need to set the context value -or- "num_ctx"
|
|
@@ -26,7 +27,7 @@
|
|
| 26 |
# GGUF model version of the Mistral Pixtral-12B for
|
| 27 |
# direct-usage with Ollama!
|
| 28 |
# Currently, there are NO USABLE OR WORKING versions
|
| 29 |
-
# of this model...
|
| 30 |
# ---------------------------------------------------
|
| 31 |
#
|
| 32 |
# Big/Giant/Huge Thank You:
|
|
|
|
| 3 |
#
|
| 4 |
# Tested with: Ollama v0.11.X-->v0.12.6(latest)
|
| 5 |
# Quantization: Q2_K (Quant created by = ggml-org)
|
| 6 |
+
# Quality: Good (Updated 2025/10/28)
|
| 7 |
+
# Real-world usability: Recommended for low-RAM Systems
|
| 8 |
+
# ------------------------------------------------------
|
| 9 |
#
|
| 10 |
# Vision Notes:
|
| 11 |
# Some users may need to set the context value -or- "num_ctx"
|
|
|
|
| 27 |
# GGUF model version of the Mistral Pixtral-12B for
|
| 28 |
# direct-usage with Ollama!
|
| 29 |
# Currently, there are NO USABLE OR WORKING versions
|
| 30 |
+
# of this model that are usable with Ollama...
|
| 31 |
# ---------------------------------------------------
|
| 32 |
#
|
| 33 |
# Big/Giant/Huge Thank You:
|