GLM-4-9B-Chat

Running GLM-4-9B-Chat locally

At Q4_K_M and 4K of context, GLM-4-9B-Chat needs about 5.9 GB — 5.2 GB of weights, 0.16 GB of KV cache and a 0.5 GB activation buffer. The smallest card in this index that clears that comfortably is the RTX 5060 Ti 8G at 8 GB, and 62 of the 63 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 1.09 GB, taking the total to 7.1 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 128K; holding all of it at Q4_K_M would need about 11 GB.

Which build to download

This index tracks 2 formats for it — GGUF, AWQ — across 3 levels. Q8_0 carries the lowest published perplexity loss at 0.4%. The fastest level measured here is AWQ INT4 at 178 tok/s on an RTX 4090, batch 1. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 and CUDA only.

Common questions

How much VRAM does GLM-4-9B-Chat need?

About 5.9 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 7.1 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.

Will GLM-4-9B-Chat run on a 8GB GPU?

Yes — at Q4_K_M and 4K context it needs about 5.9 GB, which leaves 2.1 GB spare on a RTX 5060 Ti 8G. That is the smallest card in this index that clears it comfortably; 62 of 63 do.

Which quantization of GLM-4-9B-Chat should I use?

Q8_0 has the lowest published quality loss (0.4%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q8_0, AWQ INT4.