Unverified50% confidenceFactExact time
Gemma 4 E2B was LoRA-fine-tuned and exported as Q4_K_M GGUF (3.4 GB), run on CPU by llama.cpp's llama-server, to draft two candidate replies and filter memories.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGemma 4 (local gemma4, 7.5B Q4, running via Ollama on a 4 GB laptop GPU) successfully mapped 7 suppliers, with 1–6 attempts each; IndiGo, SpiceJet, and one NDC airline failed to converge after 11 attempts and were ultimately completed by hand.70% similarUnverifiedVKORE's benchmark test uses Google's open-source Gemma 4 26B model, running on an eight-card, 32-chip Korean NPU server.69% similarUnverifiedThe experiment uses an n1-standard-2 VM, a single passively cooled Tesla T4, driver 615.71.09, vLLM 0.29.0, with the model being Gemma 4 E2B at 4-bit weights, single request, greedy decoding, 256 tokens per output.69% similarUnverifiedFor sliding-window models such as Gemma 4, TurboQuant KV cache and KV cache quantization have been added.66% similarUnverifiedGemma 3 1B is a small open-source model released by Google, with about one billion parameters, and can run on an ordinary laptop CPU.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062477API
curl https://kongchang.com/api/v1/knowledge/claims/1062477MCP
get_claim(id=1062477)