● FitLLM — fit receipt · Q4_K_M · 8K tokens ctx · KV F16 · engine 2.16.0 · revision f1e3678550d69a40971615209e14e399144b2272 · release manifest

GLM-4.7-Flash on RTX 4090

FITS ✓

weights	KV cache	overhead	reserve	total	free
17.8 GB	0.4 GB	2.4 GB	2.0 GB	22.6 / 24 GB	1.4 GB

Max context at this quant: ~10K tokens

Active structural premises

mla-compressed-latent-cache — KV memory assumes a compressed-latent MLA artifact or mode; legacy non-MLA GGUF or an explicitly uncompressed mode invalidates this estimate.

Replay: npx fitllm-engine "GLM-4.7-Flash" --gpu "RTX 4090" · JSON · interactive

live fit badge — embed: ![fits](https://img.shields.io/endpoint?url=https%3A%2F%2Ffitllm.run%2Fapi%2Fbadge%3Fmodel%3DGLM-4.7-Flash%26gpu%3DRTX%2B4090%26quant%3DQ4_K_M%26ctx%3D8192%26kv%3D16)

Computed by the open fitllm-engine (MIT) from official config.json values — estimates; runtime varies. Ran it for real? Challenge this prediction — measured reports calibrate the engine for everyone.