Unverified50% confidenceFactExact time
For Kimi K3, the VRAM requirement answers given by five popular pages were 594 GB, 1.51 TB, 1.68 TB, and "can't run it", and for the Q4 quantized requirement there were two claims, "about 800 GB" and 1.2 TB.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedFor ModelFit on Kimi K3 (unsloth repository), the UD-Q1_0 quantization has a measured file size of 466.4 GB and requires 561.1 GB of VRAM/RAM at an 8K context; UD-Q4_K_XL has a measured file size of 1.51 TB and requires about 1.6 TB; F16 is about 3 TB.78% similarUnverifiedKimi K2在FP16精度下仅模型权重就需要数百GB显存，INT4量化可将显存需求压缩至约四分之一76% similarUnverifiedKimi K3 requires approximately 1.5 TB of memory under Q4 quantization, potentially meaning four Macs would need to be linked together.71% similarVerifiedA model with 70 billion parameters that originally requires 80 GB of VRAM requires only about 40 GB of memory after 4-bit quantization (Q4_K_M level), with inference quality loss typically within 3%–8% on most benchmarks.69% similarUnverifiedMoonshot AI's Kimi K3 has 2.8 trillion parameters, with model files exceeding 1,500 GB.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054735API
curl https://kongchang.com/api/v1/knowledge/claims/1054735MCP
get_claim(id=1054735)