Qwen2.5-Coder 7B Instruct

Running Qwen2.5-Coder 7B Instruct locally

At Q4_K_M and 4K of context, Qwen2.5-Coder 7B Instruct needs about 5.1 GB — 4.4 GB of weights, 0.22 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 63 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 1.53 GB, taking the total to 6.8 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 13 GB.

Which build to download

This index tracks 3 formats for it — GGUF, AWQ, EXL2 — across 3 levels. EXL2 4.65bpw carries the lowest published perplexity loss at 2.0%. The fastest level measured here is EXL2 4.65bpw at 248 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 Qwen2.5-Coder 7B Instruct need?

About 5.1 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 6.8 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 Qwen2.5-Coder 7B Instruct run on a 8GB GPU?

Yes — at Q4_K_M and 4K context it needs about 5.1 GB, which leaves 2.9 GB spare on a RTX 5060 Ti 8G. That is the smallest card in this index that clears it comfortably; 63 of 63 do.

Which quantization of Qwen2.5-Coder 7B Instruct should I use?

EXL2 4.65bpw has the lowest published quality loss (2.0%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, AWQ INT4, EXL2 4.65bpw.