Ollama Library · llama
Can I run wizardlm2?
State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
7B parameters32K contexttextApache License9 builds
wizardlm2 system requirements
Memory needed at 4K context, counting model weights, KV cache, compute buffers and runtime overhead. Download sizes come from the official Ollama registry.
| Build | Quantization | Download | Memory needed |
|---|---|---|---|
| wizardlm2:7b | Q4_0 | 3.8 GB | ~5.9 GB(est.) |
| wizardlm2:7b-q4_K_M | Q4_K_M | 4.1 GB | ~6.2 GB(est.) |
| wizardlm2:7b-q5_K_M | Q5_K_M | 4.8 GB | ~7.2 GB(est.) |
| wizardlm2:7b-q6_K | Q6_K | 5.5 GB | ~8.3 GB(est.) |
| wizardlm2:7b-q8_0 | Q8_0 | 7.2 GB | ~10.6 GB(est.) |
| wizardlm2:7b-fp16 | F16 | 13.5 GB | ~19.7 GB(est.) |
| wizardlm2:8x22b-q4_0 | Q4_0 | 74.0 GB | ~106.3 GB(est.) |
| wizardlm2:8x22b-q8_0 | Q8_0 | 139.2 GB | ~199.4 GB(est.) |
Figures marked (est.) approximate the KV cache because this model's architecture details are not published. They are indicative rather than exact.
How to run wizardlm2 locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run wizardlm2:7b - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about wizardlm2
- How much VRAM do I need to run wizardlm2?
- At 4K context, the smallest published build of wizardlm2 (Q4_0) needs roughly 5.9 GB of GPU memory once weights, KV cache, compute buffers and runtime overhead are counted. Bigger quantizations and longer context windows need more. It can also run partly or entirely on the CPU using system RAM, more slowly.
- Can I run wizardlm2 without a dedicated GPU?
- Yes, but slowly. Without a GPU the model runs on the CPU using system RAM, which usually means a few tokens per second rather than dozens. You would need at least 5.9 GB of free RAM for the smallest build.
- How big is the wizardlm2 download?
- The smallest published build is 3.8 GB. There are 9 builds in total, the largest being 261.9 GB. Leave some extra free disk space beyond the download itself.
- How do I run wizardlm2 locally?
- Install Ollama, then run "ollama run wizardlm2:7b" in a terminal. The weights download on first use and an interactive session opens.
Will wizardlm2 run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Model data from the official Ollama registry · verified 13/09/2026