don't walk, run 🙌🏼 llama-server -hf unsloth/MiniMax-M3-GGUF:UD-Q4_K_M
if you're gpu poor like me, start with this 🫡 llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q8_0
Julien Chaumond@julien_c
run local models TODAY
5:23 AM · Jun 13, 2026 · 4.2K Views
Sentiment
Users call llama-server their favorite for running local MiniMax and Gemma models due to its standout performance.
Pos
100.0%
Neg
0.0%
1 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS1.1KLIKES3RETWEETS2
merve@mervenoyann
llama-server is my favorite hands down
merve@mervenoyann
don't walk, run 🙌🏼 llama-server -hf unsloth/MiniMax-M3-GGUF:UD-Q4_K_M
if you're gpu poor like me, start with this 🫡 llama-server -hf unsloth/gemma-4-E2B-it-GGUF:Q8_0
1hViews 1.1KLikes 3Bookmarks 0
Alex YGift@Radipdegen
@mervenoyann gpu poor tag hits a little too close to home rn
how bad is gemma on a laptop without a dedicated card?
1h