Unverified50% confidenceFactExact time
SmolLM2-360M-Instruct has only 360 million parameters, and after quantization its size can be kept at the level of several hundred MB.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn FP16 precision, large models require approximately 2 GB of VRAM per 1 billion parameters.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.70% similarUnverifiedThe model has 1.91M parameters, and after int8 quantization the weights occupy 1.97 MB, which is 49.8% of the Ryzen 5 3400G's 4 MB L3 cache.69% similarUnverifiedQuantprobe claims to enable a machine with only 6GB of VRAM and 16GB of RAM to run 30B-class models at 22 tokens/s.69% similarUnverifiedFor 1 million tokens, the KV Cache alone can consume hundreds of GB of VRAM at FP16 precision, far exceeding the 80 GB capacity limit of a single A100/H100.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059656API
curl https://kongchang.com/api/v1/knowledge/claims/1059656MCP
get_claim(id=1059656)