Export
Q4_K_M
/wiki/q4-k-m
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in Claude
Sending this to someone?
MarkdownPlain text for notes apps and AI chats
WordA document to edit and annotate
PDFA4, for printing and sharing
ZIPEverything: the documents, the data, and instructions for AI assistants
With its linksA pack for Claude, ChatGPT, Gemini or NotebookLM, or STIX and CSV, from the console
Share the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
stub ·
3 feeds
Q4_K_M
Quantization format with lower throughput (17.57 tok/s) but higher quality
Snapshot
- Category
- 4-bit quantization 1 source
Intelligence coverage
Quantization format with lower throughput (17.57 tok/s) but higher quality.
Drawn from 1 news source; the facts and relationships below show where each detail comes from.
Facts 1
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Category | 4-bit quantization | low | 1 | 4 |
Part of 1
Official links
No official links recorded yet.
Work here? Claim this page with a verified company email or DNS record.
Frequently mentioned together 9
Sources 6
- Making Local LLMs Usable on 8GB GPUs · HackerNoon
- Shapelearn Qwen 3.8 27B (13.1 GB VRAM) · Hacker News (YC)
- Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses · Lobsters
- Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses · Hacker News (YC)
- Run Qwen3.8 27B locally: real numbers from my Mac Studio · Hacker News (YC)
5 of 6 sources shown · Pro unlocks the full list