HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
GLM-5.2: The Most Powerful Open Model yet and the Brutal Reality of Running It
vettedconsumer.com
27 comments
3 days ago
ermantrout
43 points
2.
▲
Show HN: Quant Picker – which GGUF file fits your model and machine
vettedconsumer.com
discuss
9 days ago
ermantrout
20 points
3.
▲
Show HN: Local LLM Hardware Calculator
vettedconsumer.com
discuss
17 hours ago
ermantrout
3 points
4.
▲
Why long context eats your VRAM: the KV cache explained
vettedconsumer.com
discuss
6 days ago
ermantrout
3 points
5.
▲
Prompt processing vs. generation: two phases, opposite bottlenecks
vettedconsumer.com
discuss
4 days ago
ermantrout
2 points
6.
▲
Mixture-of-Experts (Moe), Explained: Why "Active Parameters" Decide What Runs
vettedconsumer.com
discuss
10 days ago
ermantrout
2 points
7.
▲
GGUF vs. GPTQ vs. AWQ: The Plain-English Guide to LLM Quantization
vettedconsumer.com
discuss
11 days ago
ermantrout
2 points
8.
▲
GGUF vs. GPTQ vs. AWQ: The Plain-English Guide to LLM Quantization
vettedconsumer.com
discuss
16 days ago
ermantrout
2 points