Fit receipt — a fixed address for one verdict

GLM-4.7-Flash on Mac 32GB

WON'T FIT ✗

Conditions: 8-bit · 8K context · KV F16

weights	KV cache	overhead	reserve	total	short by
29.1 GB	0.4 GB	3.8 GB	8.5 GB	41.8 / 32 GB	9.8 GB

→ Drop the weights to 4-bit and it fits (KV unchanged).

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 "GLM-4.7-Flash" --mac 32 --quant 8 --ctx 8192 --kv 16 · 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%26ram%3D32%26quant%3D8%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.

engine 2.21.4 · revision 2dca33db8c822bb2348949b5c54797d86a869202 · release manifest