GLM 4.7 Flash 30B-A3B
A compact mixture-of-experts model for reasoning, coding and tool use. The complete 30B model must fit in memory, not just its 3B active parameters.
Exact local Ollama manifest and configuration checked on 2026-10-20. Memory figures are conservative planning estimates; no DeviceTerra inference or speed test is claimed. Requires Ollama 0.15.0 or newer. Requires Ollama 0.14.3 or newer. All 30B weights need storage; active parameter count is not the memory footprint. Store the complete 30B weights; 3B active does not mean a 3B download.
- Official model source
- Official engine artifact
Will it run?
MamiLens uses 35 GB as a conservative planning floor for this profile and its listed quantization. This is not measured speed. Processor, backend support, context length, memory bandwidth and other applications still affect the result.
Check your complete system →What is it useful for?
Suggested Ollama artifact
Confirm the tag on the official page before downloading, then run:
ollama run glm-4.7-flash:q4_K_MStart with a representative non-sensitive task. Record the exact runtime, quantization, context, load time, generation speed, memory use and answer quality.
Evidence and limits
Published context: 198K artifact maximum; practical context depends on memory. The source establishes specifications; it does not guarantee that maximum context fits at the MamiLens minimum RAM floor.