# CodeLlama 34b Python hf [Canonical model page](https://headlessthrones.com/models/codellama-34b-python-hf) · [Model library](https://headlessthrones.com/models) Public catalog reference from Headless Thrones. Exact catalog ID: `codellama-34b-python-hf`. Catalog source-check date: 2026-10-23. This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial. Current catalog answers ## What to know about CodeLlama 34b Python hf AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026. [Exact model](https://headlessthrones.com/models/codellama-34b-python-hf#model-answer-identity) · [Access](https://headlessthrones.com/models/codellama-34b-python-hf#model-answer-access) · [Token limits](https://headlessthrones.com/models/codellama-34b-python-hf#model-answer-context) · [Inputs & outputs](https://headlessthrones.com/models/codellama-34b-python-hf#model-answer-modalities) · [License](https://headlessthrones.com/models/codellama-34b-python-hf#model-answer-license) · [Weight details](https://headlessthrones.com/models/codellama-34b-python-hf#model-answer-repository) ### Which CodeLlama 34b Python hf does this page describe? CodeLlama 34b Python hf is a model record from **Meta** in the Code Llama family. [Source](https://huggingface.co/meta-llama/CodeLlama-34b-Python-hf) The recorded model identifier or checkpoint is `meta-llama/CodeLlama-34b-Python-hf`. Use that exact identifier when checking documentation or a provider listing. [Source](https://huggingface.co/meta-llama/CodeLlama-34b-Python-hf) ### How can you access CodeLlama 34b Python hf? The catalog documents **Open weights** access for CodeLlama 34b Python hf. [Source](https://huggingface.co/meta-llama/CodeLlama-34b-Python-hf) As of the catalog check, this version was listed as available. [Source](https://huggingface.co/meta-llama/CodeLlama-34b-Python-hf) Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. ### What are CodeLlama 34b Python hf's context and output limits? The documented **context window is 100,000 tokens**. [Source](https://github.com/meta-llama/codellama/blob/main/MODEL_CARD.md) A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance. Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity. ### What can CodeLlama 34b Python hf receive and generate? Documented inputs: **text**. [Source](https://github.com/meta-llama/codellama/blob/main/MODEL_CARD.md) Documented outputs: **text**. [Source](https://github.com/meta-llama/codellama/blob/main/MODEL_CARD.md) Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation. ### What license is recorded for CodeLlama 34b Python hf? The recorded license label is **Custom commercial Code Llama license**. [Source](https://github.com/meta-llama/codellama/blob/main/MODEL_CARD.md) Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service. ### What is documented about the CodeLlama 34b Python hf checkpoint? This evidence refers to `meta-llama/CodeLlama-34b-Python-hf` at recorded revision `2462f4ca0933c022374e2cac879cc6d296b3f3b1`, checked October 23, 2026. [Repository metadata](https://huggingface.co/api/models/meta-llama/CodeLlama-34b-Python-hf) Safetensors metadata records **33,743,970,304 stored parameters**. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. [Repository metadata](https://huggingface.co/api/models/meta-llama/CodeLlama-34b-Python-hf) Recorded architecture class: `LlamaForCausalLM`. [Repository metadata](https://huggingface.co/api/models/meta-llama/CodeLlama-34b-Python-hf) Repository task tag: `text-generation`. A task tag identifies a distribution category; it does not measure performance on that task. [Repository metadata](https://huggingface.co/api/models/meta-llama/CodeLlama-34b-Python-hf) Listed library: `transformers`. Check that library's version and model support before loading the weights. [Repository metadata](https://huggingface.co/api/models/meta-llama/CodeLlama-34b-Python-hf) Repository language labels: code. These labels are not independent evaluations of language quality. [Repository metadata](https://huggingface.co/api/models/meta-llama/CodeLlama-34b-Python-hf) Repository access gate: `manual`. This records the repository's gate setting when checked; licensing and use terms still apply. [Repository metadata](https://huggingface.co/api/models/meta-llama/CodeLlama-34b-Python-hf) Read the retrieved model card for setup and qualifications. [Model card](https://huggingface.co/meta-llama/CodeLlama-34b-Python-hf/resolve/2462f4ca0933c022374e2cac879cc6d296b3f3b1/README.md) **Catalog qualifications:** Vendor describes up to 100K inference context for most variants and 16K training sequences. Python 70B and Instruct 70B excluded from that stated inference claim. [Source 1](https://huggingface.co/api/models/meta-llama/CodeLlama-34b-Python-hf) · [Source 2](https://huggingface.co/meta-llama/CodeLlama-34b-Python-hf/resolve/2462f4ca0933c022374e2cac879cc6d296b3f3b1/README.md) **Evidence still missing here:** knowledge and training-data cutoffs and tested hardware requirements. Missing documentation is not evidence that a feature is unavailable. Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model. Keep the exact version in view ## Other Code Llama models from Meta. These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses. ### [CodeLlama 13b hf](https://headlessthrones.com/models/codellama-13b-hf) Open weights · 100,000 context tokens ### [CodeLlama 13b Instruct hf](https://headlessthrones.com/models/codellama-13b-instruct-hf) Open weights · 100,000 context tokens ### [CodeLlama 13b Python hf](https://headlessthrones.com/models/codellama-13b-python-hf) Open weights · 100,000 context tokens ### [CodeLlama 34b hf](https://headlessthrones.com/models/codellama-34b-hf) Open weights · 100,000 context tokens ### [CodeLlama 34b Instruct hf](https://headlessthrones.com/models/codellama-34b-instruct-hf) Open weights · 100,000 context tokens ### [CodeLlama 70b hf](https://headlessthrones.com/models/codellama-70b-hf) Open weights · 100,000 context tokens