How much FASTER is GLM 5.2 with MTP 💪 | Local AI TEST
Credibility score: 44/100 — Mixed Credibility. Several questionable claims detected. Watch with healthy skepticism.
Claims analyzed
Video opens with a highlight reel preview of speed metrics. — Just Vibes (50/100)
Just a quick-cut montage of numbers flashing by — setting the stage for a speed test, not making a specific claim yet. ⚡️
Claiming MTP decoding sped up other models 'up to two times speed'. — Missing Context (45/100)
Says 'up to two times speed' for other models, but doesn't name a single one or give any specifics. 'Other models' is doing a lot of heavy lifting. 🤷♀️
Explains MTP uses a tiny layer to predict what a massive model would, calling it 'asking a lot'. — Confidence Mismatch (45/100)
Describes the MTP layer as 'very very small' and the main model as 'half a terabyte gigabyte' — then says 'you're asking a lot' with no actual scale. That's a lot of hand-waving. 🤏
States higher quantized models run faster, but Q2/Q3 won't speed up with NTP. — Confidence Mismatch (45/100)
Claims higher quantization makes it faster, then immediately says lower quantization (Q2/Q3) won't speed up. Kinda contradictory, no? 🤔
Guaranteed speed above 20 tokens/second, then it immediately drops. — Confidence Mismatch (45/100)
Declared 'guaranteed' above 20 tokens/second, then the live meter immediately dipped below. The guarantee had a shelf life of like, 2 seconds 💀
Claiming 'above 20 tokens a second guaranteed' while the live feed drops to 17. — Confidence Mismatch (45/100)
Said 'guaranteed above 20' then watched it immediately dip to 17. The 'guaranteed' part is doing some heavy lifting. 🤡
Assuming coding tasks are easier for token prediction due to structure. 🤔 — Confidence Mismatch (45/100)
Assuming 'usually guesses the right tokens' for coding without showing the data. That's a vibe, not a fact. 🔮
Stating the MTP enabled result as 15.2 tokens/second. — Confidence Mismatch (45/100)
Said '15.2 tokens a second with MTP enabled' but the previous test was 15.8. Which one is it? 🤨
Testing Flappy Bird Zero with MTP, claiming over 20 tokens/second but showing 15.4 and 15. — Confidence Mismatch (45/100)
Says 'over 20 tokens a second' then immediately shows 15.4 and 15. The numbers are doing their own thing 🤡
Comparing MTP disabled vs. enabled, but the numbers are all over the place 🤡 — Confidence Mismatch (45/100)
Starts with 'nice stable 15.3' then immediately lists 11, 12, 14, 19, and ends with 'abysmal 13.4.' Which one is it, chief? 🤷♂️
Predicting MTP will be 'bonkersly bad' at creative writing, then showing it struggle. — Confidence Mismatch (45/100)
Called it 'bonkersly bad' before the test, then showed it underperform. The prediction was a bit of a self-fulfilling prophecy, no? 🔮
Downplaying the cost of 5 gigs of memory with a shrug 🤷♂️ — Loaded Language (45/100)
Dismissing 5 gigs as 'probably not worth it' is a bit of an understatement for many users. That's a lot of RAM for a 'maybe' speed boost. 💾
Downplays the cost of 5 gigs of memory with a shrug 🤷♂️ — Loaded Language (45/100)
Dismissing 5 gigs of memory as 'probably not worth it' is a casual way to frame a significant resource cost. 💾
Admits MDP isn't performing well, despite improving accuracy from 10% to 70%. — Confidence Mismatch (45/100)
Went from 'Whoa' at 50% to 'not doing too well' at 70%. The goalposts are moving faster than the tokens. 🥅💨
Claims they're 'gaming' with MDP disabled, implying a performance boost. — Loaded Language (45/100)
Using 'gaming' to describe performance with MDP off — sounds like a win, but it's just the baseline. 🎮
The numbers are all over the place, and the speaker attributes it to 'memory clearing' 🤷♂️ — Confidence Mismatch (45/100)
The token per second numbers are jumping around, and the explanation is 'maybe my memory needed clearing.' That's not exactly a scientific variable control, chief 🤡
Declares four steps are definitely slower than three in this test. — Confidence Mismatch (45/100)
Says 'definitely slower' based on one run. That's a strong word for a single data point. 😬
Speaker claims a peak of 29 tokens/second and considers it for the thumbnail. — Cherry-Picked (20/100)
Saw a peak of 29 for a second, but the average was 18. Cherry-picking the high point for the thumbnail, classic move. 📈🖼️
Rapidly listing various token-per-second results, ending with a specific 'flashed' speed. — Confidence Mismatch (45/100)
Just rattling off numbers with no context or explanation for the fluctuations. It's a speed run of stats. 💨
See the full analysis with sources and timestamps →