Microsoft · llama
Can I run phind-codellama?
Code generation model based on Code Llama.
Parameter counts and memory belong to each build below. A family can contain several sizes and tasks; fitting in memory is not a quality ranking.
Calculate memory for a build and contextphind-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-python-q4_034B parameters (tag)16K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 17.7 GB | ~20.3 GB |
| phind-codellama:34b-q4_034B parameters (tag)16K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 17.7 GB | ~20.3 GB |
| phind-codellama:34b34B parameters (tag)16K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_0 | 17.7 GB | ~20.3 GB |
| phind-codellama:34b-python-q4_K_M34B parameters (tag)16K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 18.8 GB | ~21.5 GB |
| phind-codellama:34b-q4_K_M34B parameters (tag)16K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 18.8 GB | ~21.5 GB |
| phind-codellama:34b-v2-q4_K_M34B parameters (tag)16K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q4_K_M | 18.8 GB | ~21.5 GB |
| phind-codellama:34b-python-q5_K_M34B parameters (tag)16K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 22.2 GB | ~25.1 GB |
| phind-codellama:34b-q5_K_M34B parameters (tag)16K documented maximum contextBuild sourceCatalog checked 2026-10-13 | Q5_K_M | 22.2 GB | ~25.1 GB |
Showing the 8 smallest non-alias builds. Choose any build and change the context. A context above the build's documented maximum is a hypothetical calculation, not a supported setting.
How to run phind-codellama locally
- 1.Install Ollama for Windows, macOS or Linux.
- 2.Download this exact build in a terminal:
ollama pull phind-codellama:34b-python-q4_0 - 3.Check the source for the build's task. For text generation, run
ollama run phind-codellama:34b-python-q4_0. Base/text builds may need a prompt template; an instruct build is usually the appropriate starting point for a conversation.
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 20.3 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?
- A supported CPU runtime can use system RAM. The smallest listed build needs an estimated 20.3 GB at 4K context, plus headroom for your operating system. Check the build's runtime requirements. We have not measured its speed on your CPU.
- 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 download a specific build with "ollama pull phind-codellama:34b-python-q4_0". For a build that supports text generation, use ollama run with the same tag. Check the model source for its task and prompt format.
Will phind-codellama run on your PC?
Scan your hardware once and get a verdict for this model and every build — free, no account.
Compare with similar models
Or start from your memory: 8 GB VRAM, 12 GB VRAM, 16 GB VRAM, 24 GB VRAM or a 16 GB Mac.
Model data from the official Ollama registry · verified 13/10/2026