UnslothAI 1-Bit Quantized Inkling Model Runs 30-40 TPS on Llama.cpp

DH

Combined views

4.7K

2 posts, first seen 1h ago

57 likes9 comments

Commentary on X

PK

Praveen Koka@praveenkoka

@mervenoyann @thinkymachines @UnslothAI At 1-bit precision, you've basically bet everything on binary weights. 30-40 TPS for something that trades most of its accuracy for speed, the real speedrun is measuring how wrong it still is.

6:13 AM · Jul 16, 2026

AT

Ai Trend@Ai_Trend_

@mervenoyann @thinkymachines @UnslothAI That 1-bit quant speed is seriously impressive! And good shout on the llama.cpp webUI features; the reasoning slider sounds like a great addition for exploring model behavior.

7:36 AM · Jul 16, 2026

RA

RaoulDuke@RaoulDukeDegen

@mervenoyann @thinkymachines @UnslothAI inkling being open weights from mira muratis new lab is huge for local dev work

7:01 AM · Jul 16, 2026

Combined views

4.7K

2 posts, first seen 1h ago

57 likes9 comments

9 saves

7 reposts

Sentiment

Positive85.7%14.3%Negative

Based on 8 visible X reactions from 11 accounts; directional sample.

Digg Deeper

Ask a question below.

Published answers will appear here.

Commentary on X

PK

Praveen Koka@praveenkoka

@mervenoyann @thinkymachines @UnslothAI At 1-bit precision, you've basically bet everything on binary weights. 30-40 TPS for something that trades most of its accuracy for speed, the real speedrun is measuring how wrong it still is.

6:13 AM · Jul 16, 2026

AT

Ai Trend@Ai_Trend_

@mervenoyann @thinkymachines @UnslothAI That 1-bit quant speed is seriously impressive! And good shout on the llama.cpp webUI features; the reasoning slider sounds like a great addition for exploring model behavior.

7:36 AM · Jul 16, 2026

RA

RaoulDuke@RaoulDukeDegen

@mervenoyann @thinkymachines @UnslothAI inkling being open weights from mira muratis new lab is huge for local dev work

7:01 AM · Jul 16, 2026

AH

Ahmad@TheAhmadOsman

@mervenoyann @thinkymachines @UnslothAI Look at the Opensource AI ecosystem, we're becoming stronger by the day 🦾

5:51 AM · Jul 16, 2026

View all

@danielhanchen @thinkymachines @UnslothAI it's a giant for sure 👨🏻‍🎤

7:31 AM · Jul 16, 2026

Inkling @thinkymachines 1-bit quant by @UnslothAI running 30-40 TPS 🤯 video sped up, feel free to jump at the end to check outputs also llama.cpp webui is 😍 has reasoning slider, html preview, mcp and multimodal support

5:45 AM · Jul 16, 2026

DH

Daniel Han@danielhanchen

@mervenoyann @thinkymachines @UnslothAI I was also very surprised it was quite fast haha!

7:17 AM · Jul 16, 2026

AH

Ahmad@TheAhmadOsman

@mervenoyann @thinkymachines @UnslothAI Look at the Opensource AI ecosystem, we're becoming stronger by the day 🦾

5:51 AM · Jul 16, 2026

View all

@danielhanchen @thinkymachines @UnslothAI it's a giant for sure 👨🏻‍🎤

7:31 AM · Jul 16, 2026

Inkling @thinkymachines 1-bit quant by @UnslothAI running 30-40 TPS 🤯 video sped up, feel free to jump at the end to check outputs also llama.cpp webui is 😍 has reasoning slider, html preview, mcp and multimodal support

5:45 AM · Jul 16, 2026

DH

Daniel Han@danielhanchen

@mervenoyann @thinkymachines @UnslothAI I was also very surprised it was quite fast haha!

7:17 AM · Jul 16, 2026