Microsoft · llama
Can I run phind-codellama?
Code generation model based on Code Llama.
34B parameters16K contexttextLLAMA 2 COMMUNITY LICENSE AGREEMENT18 builds
phind-codellama 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 |
|---|---|---|---|
| phind-codellama:34b-q4_0 | Q4_0 | 17.7 GB | ~25.8 GB(est.) |
| phind-codellama:34b-python-q4_0 | Q4_0 | 17.7 GB | ~25.8 GB(est.) |
| phind-codellama:34b | Q4_0 | 17.7 GB | ~25.8 GB(est.) |
| phind-codellama:34b-q4_K_M | Q4_K_M | 18.8 GB | ~27.3 GB(est.) |
| phind-codellama:34b-python-q4_K_M | Q4_K_M | 18.8 GB | ~27.3 GB(est.) |
| phind-codellama:34b-v2-q4_K_M | Q4_K_M | 18.8 GB | ~27.3 GB(est.) |
| phind-codellama:34b-q5_K_M | Q5_K_M | 22.2 GB | ~32.1 GB(est.) |
| phind-codellama:34b-python-q5_K_M | Q5_K_M | 22.2 GB | ~32.1 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 phind-codellama locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Run this in a terminal:
ollama run phind-codellama:34b-q4_0 - 3.The weights download on first run, then an interactive prompt opens.
Frequently asked questions about phind-codellama
- How much VRAM do I need to run phind-codellama?
- At 4K context, the smallest published build of phind-codellama (Q4_0) needs roughly 25.8 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 phind-codellama 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 25.8 GB of free RAM for the smallest build.
- How big is the phind-codellama download?
- The smallest published build is 17.7 GB. There are 18 builds in total, the largest being 62.9 GB. Leave some extra free disk space beyond the download itself.
- How do I run phind-codellama locally?
- Install Ollama, then run "ollama run phind-codellama:34b-q4_0" in a terminal. The weights download on first use and an interactive session opens.
Will phind-codellama 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