BotConnector
Sign in Workspace Open App

Context and memory

warning

The memory formula

Total memory at load ≈

text
model file size
+ KV cache   (scales with context length and model)
+ runtime overhead (~0.5–1 GB)

KV cache intuition

The KV cache stores per-token attention state for the whole context. Longer context = more cache:

  • A 7B model at Q4 (~4.7 GB) with 4K context: KV cache roughly 0.3–0.5 GB.
  • The same model at 32K context: KV cache grows to several GB.
  • KV cache quantization (Q8) reduces this at small quality cost where supported.

Worked examples

SetupModel fileContextKV cache (approx.)Total
7B Q4_K_M, 4K4.7 GB4K~0.5 GB~6 GB
7B Q4_K_M, 32K4.7 GB32K~4 GB~9.5 GB
14B Q4_K_M, 8K9 GB8K~1.5 GB~11 GB
30B MoE Q4, 8K19 GB8K~2 GB~22 GB

Always leave 1–2 GB headroom for the OS and the runtime itself.

Choosing context

  • Chat: 4K–8K is usually enough.
  • Long documents/code: 16K–32K if memory allows.
  • Setting context at load:
powershell
botconnector run <model> --ctx 8192

GPU offload interacts with context

The KV cache can live on GPU too. If model + KV fit in VRAM you get the full speedup; if only the model fits, cache stays in system RAM and transfers slow generation.

Troubleshooting

  • OOM at load → smaller quant, smaller context, less offload. Memory problems
  • Generation slows over time → context filling up; watch botconnector ps. Runtime problems