Comparison
codellama vs exllama
Verdict
Pick codellama if codellama offers an open-source inference framework for CodeLlama models using Python; pick exllama if exLlama provides a memory-efficient implementation of the LLaMa model with support for quantized weights, primarily aimed at users with NVIDIA GPUs from the 30-series onwards.
Markdown twin · codellama alternatives · exllama alternatives
GraphCanon updated 2w
vs
Trust & integrity
| Signal | codellama | exllama |
|---|---|---|
| Maintenance | Archived (722d since push) As of 2w · github_public_v1 | Dormant (1041d since push) As of 2w · github_public_v1 |
| Provenance | Not a fork · Organization account As of 2w · github_public_v1 | Not a fork · Personal account As of 2w · github_public_v1 |
| OSV dependency advisories | No published findings from this source as of 2026-07-11 As of 1mo · osv@v1 | Published findings As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- codellama
- Inference code for CodeLlama models
- exllama
- Memory-efficient rewrite of HF transformers for Llama with quantized weights
Stars
- codellama
- 16k
- exllama
- 2.9k
Forks
- codellama
- 1.9k
- exllama
- 220
Open issues
- codellama
- 116
- exllama
- 65
Language
- codellama
- Python
- exllama
- Python
Adopt for
- codellama
- codellama offers an open-source inference framework for CodeLlama models using Python.
- exllama
- ExLlama provides a memory-efficient implementation of the LLaMa model with support for quantized weights, primarily aimed at users with NVIDIA GPUs from the 30-series onwards.
Persona
- codellama
- -
- exllama
- -
Runtime
- codellama
- -
- exllama
- -
License
- codellama
- Other
- exllama
- MIT
Last pushed
- codellama
- Aug 12, 2024
- exllama
- Sep 30, 2023
Categories
- codellama
- Inference & Serving
- exllama
- Inference & Serving, LLM Frameworks
Trust and health
Maintenance
- codellama
- Archived (8%)
- exllama
- Dormant (18%)
Days since push
- codellama
- 722d
- exllama
- 1041d
Archived on GitHub
- codellama
- Yes
- exllama
- No
Open issues (now)
- codellama
- 116
- exllama
- 65
Owner type
- codellama
- Organization
- exllama
- User
OSV dependency advisories
- codellama
- No published findings from this source as of 2026-07-11
- exllama
- Published findings
Full report
- codellama
- Trust report
- exllama
- Trust report
Choose codellama if…
- License: codellama is Other, exllama is MIT.
- Pricing: codellama operates on an open-source model with freedoms for both researchers and commercial entities. Costs will arise from hosting and running environments where required..
- Requirements: Users should familiarize themselves with the acceptable use policy to align their projects accordingly.; Dependencies include Python, which must be installed for using codellama..
- Tags unique to codellama: codellama, inference.
- If you need to work with the CodeLlama models specifically and benefit from their specialized capabilities in coding tasks, codellama provides tailored support that may outperform generic solutions.
When NOT to use codellama
- If you are working on projects that do not align with CodeLlama's acceptable use policy or require compliance with specific industry standards beyond what codellama offers.
- For tasks that demand a different primary programming language other than Python, as codellama is primarily developed around the Python ecosystem.
Choose exllama if…
- License: exllama is MIT, codellama is Other.
- Tags unique to exllama: docker, llama model, memory-efficient, nvidia gpu.
- Also covers LLM Frameworks.
- exllama ships Docker support for self-hosted deployment.
- - When deploying LLaMa models on NVIDIA GPUs from the 30-series or later that have strong FP16 support.
When NOT to use exllama
- - If you are operating older GPUs such as Pascal series, which lack robust FP16 support; alternatives like AutoGPTQ might perform better.
- - In scenarios that involve AMD GPU hardware (due to limited testing and optimization efforts).
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (meta-llama/codellama) · observed Aug 5, 2026
- GitHub forks (meta-llama/codellama) · observed Aug 5, 2026
- Last push (meta-llama/codellama) · observed Aug 12, 2024
- License file (Other) · observed Aug 5, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (turboderp/exllama) · observed Aug 7, 2026
- GitHub forks (turboderp/exllama) · observed Aug 7, 2026
- Last push (turboderp/exllama) · observed Sep 30, 2023
- License file (MIT) · observed Aug 7, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: codellama 16k · exllama 2.9k (synced Aug 5, 2026).
Common questions
- What is the difference between codellama and exllama?
- codellama: Inference code for CodeLlama models. exllama: Memory-efficient rewrite of HF transformers for Llama with quantized weights. See the comparison table for live GitHub stats and shared categories.
- When should I choose codellama over exllama?
- Choose codellama over exllama when License: codellama is Other, exllama is MIT; Pricing: codellama operates on an open-source model with freedoms for both researchers and commercial entities. Costs will arise from hosting and running environments where required.; Requirements: Users should familiarize themselves with the acceptable use policy to align their projects accordingly.; Dependencies include Python, which must be installed for using codellama.; Tags unique to codellama: codellama, inference; If you need to work with the CodeLlama models specifically and benefit from their specialized capabilities in coding tasks, codellama provides tailored support that may outperform generic solutions.
- When should I choose exllama over codellama?
- Choose exllama over codellama when License: exllama is MIT, codellama is Other; Tags unique to exllama: docker, llama model, memory-efficient, nvidia gpu; Also covers LLM Frameworks; exllama ships Docker support for self-hosted deployment; - When deploying LLaMa models on NVIDIA GPUs from the 30-series or later that have strong FP16 support.
- When should I avoid codellama?
- If you are working on projects that do not align with CodeLlama's acceptable use policy or require compliance with specific industry standards beyond what codellama offers. For tasks that demand a different primary programming language other than Python, as codellama is primarily developed around the Python ecosystem.
- When should I avoid exllama?
- - If you are operating older GPUs such as Pascal series, which lack robust FP16 support; alternatives like AutoGPTQ might perform better. - In scenarios that involve AMD GPU hardware (due to limited testing and optimization efforts).
- Is codellama or exllama more popular on GitHub?
- codellama has more GitHub stars (16,280 vs 2,937). Stars measure visibility, not whether either tool fits your constraints.
- Are codellama and exllama open source?
- Yes - both are open-source projects on GitHub (codellama: Other, exllama: MIT).
- Where can I find alternatives to codellama or exllama?
- GraphCanon lists graph-backed alternatives at codellama alternatives and exllama alternatives (codellama markdown twin, exllama markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, codellama or exllama?
- codellama: Archived. exllama: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for codellama and exllama?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: codellama trust report; exllama trust report.