Qwen 2.5 Coder 32B — VRAM, speed & local setup
Written by Jakub Rusinowski · Last updated
The current SOTA for local coding. Matches GPT-4 in many coding benchmarks. Fits on 24GB cards.
Qwen 2.5 Coder 32B needs about 20 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
VRAM and speed by quantization
Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.
| Quant | Memory | VRAM | Speed (est.) | Fit |
|---|---|---|---|---|
| Q2_K 2.63 bpw | 13.5 GB | ~57 tok/s | Fits | |
| Q3_K_M 3.41 bpw | 16.6 GB | ~46 tok/s | Fits | |
| Q4_K_M 4.83 bpw | 22.3 GB | ~34 tok/s | Tight | |
| Q5_K_M 5.67 bpw | 25.6 GB | ~4 tok/s | Offload | |
| Q6_K 6.56 bpw | 29.2 GB | ~4 tok/s | Offload | |
| Q8_0 8.50 bpw | 36.9 GB | ~3 tok/s | Offload | |
| F16 16.00 bpw | 66.9 GB | — | Too big |
Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Qwen 2.5 Coder 32B VRAM calculator →
Get Qwen 2.5 Coder 32B running
The cheapest catalogued GPU that runs Qwen 2.5 Coder 32B is the AMD Radeon RX 7900 XTX (24 GB).
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
How to run Qwen 2.5 Coder 32B
Install Ollama, then run:
ollama run qwen2.5-coder:32bSpecifications
Curated — A hand-written entry from before this catalogue recorded its sources. The figures are long-standing but their provenance is not on file.
- Parameters
- 32 Billion
- Context window
- 128,000
- Architecture
- Dense
- Provider
- Alibaba Cloud
- Licence
- Apache 2.0
- Practical deployment
- Single consumer GPU
- Specified at
- Q4_K_M
- System RAM
- 32 GB
- Record updated
- 2024-11-12
Commercial use permitted. No usage restrictions beyond attribution.
Quality and use cases
Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.
Can I run Qwen 2.5 Coder 32B on my GPU?
- Qwen 2.5 Coder 32B on AMD Radeon RX 7800 XT
- Qwen 2.5 Coder 32B on AMD Radeon RX 7900 XT
- Qwen 2.5 Coder 32B on AMD Radeon RX 7900 XTX
- Qwen 2.5 Coder 32B on AMD Radeon RX 9060 XT 16GB
- Qwen 2.5 Coder 32B on AMD Radeon RX 9060 XT 8GB
- Qwen 2.5 Coder 32B on AMD Radeon RX 9070
- Qwen 2.5 Coder 32B on AMD Radeon RX 9070 XT
- Qwen 2.5 Coder 32B on AMD Ryzen AI Max+ 395
- Qwen 2.5 Coder 32B on Apple M1
- Qwen 2.5 Coder 32B on Apple M1 Max
- Qwen 2.5 Coder 32B on Apple M1 Pro
- Qwen 2.5 Coder 32B on Apple M2 Max
- Qwen 2.5 Coder 32B on Apple M2 Pro
- Qwen 2.5 Coder 32B on Apple M3 Max
- Qwen 2.5 Coder 32B on Apple M3 Pro
- Qwen 2.5 Coder 32B on Apple M4
- Qwen 2.5 Coder 32B on Apple M5
- Qwen 2.5 Coder 32B on Apple M5 Pro
- Qwen 2.5 Coder 32B on Intel Arc B570
- Qwen 2.5 Coder 32B on Intel Arc B580
- Qwen 2.5 Coder 32B on NVIDIA A100 80GB (PCIe)
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 3060 (12GB)
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 3070
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 3070 Ti
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 3080 (10GB)
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 3090
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4060
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4060 Ti 16GB
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4070
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4070 Super
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4070 Ti
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4070 Ti Super
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4080
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4080 Super
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 4090
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 5060
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 5060 Ti 16GB
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 5060 Ti 8GB
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 5070
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 5070 Ti
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 5080
- Qwen 2.5 Coder 32B on NVIDIA GeForce RTX 5090
- Qwen 2.5 Coder 32B on NVIDIA H100 80GB (PCIe)
- Qwen 2.5 Coder 32B on NVIDIA L40S
- Qwen 2.5 Coder 32B on NVIDIA RTX 6000 Ada Generation
- Qwen 2.5 Coder 32B on NVIDIA RTX PRO 6000 Blackwell
Other Qwen 2.5 Family sizes
Qwen 2.5 Coder 32B — frequently asked questions
How much VRAM does Qwen 2.5 Coder 32B need?
About 20 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.
Does Qwen 2.5 Coder 32B run on an RTX 4090 (24 GB)?
Yes. Qwen 2.5 Coder 32B needs about 20 GB at Q4_K_M, inside a 24 GB card, at an estimated 34 tokens/sec.
How do I run Qwen 2.5 Coder 32B locally?
Install Ollama and run `ollama run qwen2.5-coder:32b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.
What other sizes does Qwen 2.5 Family come in?
Qwen 2.5 Coder 32B (20 GB), Qwen 2.5 14B Instruct (9 GB), Qwen 2.5 7B Instruct (5 GB), Qwen 2.5 72B Instruct (44 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.