Unverified50% confidenceBenchmarkExact time
On the Aider Polyglot coding test, DeepSeek at full precision scored 71.6%, Unsloth's 4-bit dynamic version scored 69.7%, the 2-bit version scored 65.8%, while a competing quantization solution of the same 2-bit depth and file size scored only 56.6%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedThe final results were 6/6 numerical tests passed, 0 dependency vulnerabilities, 1,775 modules transformed, production JavaScript of approximately 213.6 kB, and approximately 68.5 kB after Gzip compression.67% similarUnverified初代 DeepSeek Math 7B 在 MATH 竞赛基准测试中以70亿参数达到 51.7% 的正确率67% similarUnverifiedOllama分发的DeepSeek R1各版本均经过GGUF格式量化处理（通常为Q4_K_M或Q8_0精度），将每个参数从16位浮点数压缩至4-8位，显存占用减少50%-75%，推理质量损失通常在5%以内67% similarUnverified在覆盖九大维度共403道题的测试中，Muse-Glimmer-30B综合均分为76.04，比Corpus 3.6 27B的75.57高出0.47分65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/909120API
curl https://kongchang.com/api/v1/knowledge/claims/909120MCP
get_claim(id=909120)