Tenker litt på denne mtp dagsaktuelle saker
August 22, 2025 at 10:25 AM
Tenker litt på denne mtp dagsaktuelle saker
MTP fanbook sample is here!! 😭😭😭😭
September 28, 2026 at 5:37 AM
MTP fanbook sample is here!! 😭😭😭😭
November 12, 2024 at 10:12 AM
Trump didn’t storm off the MTP interview. He hobbled off it.
June 8, 2026 at 6:07 PM
Trump didn’t storm off the MTP interview. He hobbled off it.
Chasten Buttigieg on Scott Bessent's MTP remarks this morning:
“Baubles?”
Dude lives in a 22 million dollar Barbie mansion."
“Baubles?”
Dude lives in a 22 million dollar Barbie mansion."
March 16, 2025 at 3:22 PM
Chasten Buttigieg on Scott Bessent's MTP remarks this morning:
“Baubles?”
Dude lives in a 22 million dollar Barbie mansion."
“Baubles?”
Dude lives in a 22 million dollar Barbie mansion."
October 25, 2024 at 10:43 PM
Kind of surprised they allowed Trump to go on MTP in this full end of he mad king phase. Sad.
June 8, 2026 at 2:09 PM
Kind of surprised they allowed Trump to go on MTP in this full end of he mad king phase. Sad.
they should have given MTP to Mehdi Hassan
November 24, 2024 at 6:13 AM
they should have given MTP to Mehdi Hassan
Two of Chuck Todd's favorite guests on MTP were Hugh Hewitt and David Brody.
This comment further illustrates perfectly why he was so incredibly useless.
This comment further illustrates perfectly why he was so incredibly useless.
August 28, 2025 at 2:28 AM
Two of Chuck Todd's favorite guests on MTP were Hugh Hewitt and David Brody.
This comment further illustrates perfectly why he was so incredibly useless.
This comment further illustrates perfectly why he was so incredibly useless.
Never gets old
August 25, 2026 at 11:26 PM
Never gets old
August 5, 2025 at 9:35 PM
Qwen3.6 now runs 2x faster with MTP GGUFs! Run locally on just 18GB RAM. ⚡️
MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.
Qwen3.6-27B MTP runs at 160 tokens/s. 35B-A3B reaches 240 t/s.
GGUFs: huggingface.co/unsloth/Qwen...
Guide: unsloth.ai/docs/models/...
MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.
Qwen3.6-27B MTP runs at 160 tokens/s. 35B-A3B reaches 240 t/s.
GGUFs: huggingface.co/unsloth/Qwen...
Guide: unsloth.ai/docs/models/...
May 18, 2026 at 1:42 PM
Qwen3.6 now runs 2x faster with MTP GGUFs! Run locally on just 18GB RAM. ⚡️
MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.
Qwen3.6-27B MTP runs at 160 tokens/s. 35B-A3B reaches 240 t/s.
GGUFs: huggingface.co/unsloth/Qwen...
Guide: unsloth.ai/docs/models/...
MTP enables Qwen3.6 to generate ~1.4–2.2× faster with no accuracy change.
Qwen3.6-27B MTP runs at 160 tokens/s. 35B-A3B reaches 240 t/s.
GGUFs: huggingface.co/unsloth/Qwen...
Guide: unsloth.ai/docs/models/...
Gemma 4 now runs 2x faster with MTP GGUFs! Run locally on just 6GB RAM. ⚡️
MTP enables Google Gemma 4 run ~1.4–2.2× faster with no accuracy loss.
Gemma 4 12B MTP can run at 162 t/s vs. 52 t/s without MTP. 31B reaches 101 t/s.
GGUFs + Guide: unsloth.ai/docs/models/...
MTP enables Google Gemma 4 run ~1.4–2.2× faster with no accuracy loss.
Gemma 4 12B MTP can run at 162 t/s vs. 52 t/s without MTP. 31B reaches 101 t/s.
GGUFs + Guide: unsloth.ai/docs/models/...
June 11, 2026 at 4:28 PM
Gemma 4 now runs 2x faster with MTP GGUFs! Run locally on just 6GB RAM. ⚡️
MTP enables Google Gemma 4 run ~1.4–2.2× faster with no accuracy loss.
Gemma 4 12B MTP can run at 162 t/s vs. 52 t/s without MTP. 31B reaches 101 t/s.
GGUFs + Guide: unsloth.ai/docs/models/...
MTP enables Google Gemma 4 run ~1.4–2.2× faster with no accuracy loss.
Gemma 4 12B MTP can run at 162 t/s vs. 52 t/s without MTP. 31B reaches 101 t/s.
GGUFs + Guide: unsloth.ai/docs/models/...
