Unverified60% confidenceFactExact time
A 70B parameter model after Q4 quantization often still has a lower perplexity than a 13B model under Q8 or even FP16.
2
Sources
60%
Confidence
Long-term
Relevance
8/14/2026
First Seen
Sources
看懂GGUF量化：Q4_K_M与Q4_K_S的真正区别
Related Claims
UnverifiedQ4_K_M is the most mainstream balanced quantization choice, with perplexity loss typically below 1%; Q2_K can compress a 70B model to approximately 26GB but with a noticeable quality degradation.71% similarUnverifiedUsing Qwen3-4B as the base model, applying supervised fine-tuning with only counterexample data causes the model's ability to recognize true theorems to collapse from 0.27 to 0.00.71% similarUnverifiedThe computational load of a single inference pass for a 2B parameter model is approximately one thirty-fifth that of a 70B model.70% similarUnverifiedReducing model parameters from 70B to 7B lowers both the VRAM required for inference and the per-request computation by approximately one order of magnitude.70% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/745192API
curl https://kongchang.com/api/v1/knowledge/claims/745192MCP
get_claim(id=745192)