Why this fit
Teams evaluating AI models, assistants and generative workflows — free to start, source available on GitHub.
AI / Catalogue record
Free
Catalogue record
github.com
ExLlamaV2
A fast inference library for running LLMs locally on modern consumer-class GPUs | GPTQ/EXL2 | GPU | ❌ | Python/C++ | Text-Gen
Checked Oct 27, 2026Evidence completeness: evidenceREADME refreshed Oct 16, 2026
Field notes
Useful context before you commit.
A fast inference library for running LLMs locally on modern consumer-class GPUs | GPTQ/EXL2 | GPU | ❌ | Python/C++ | Text-Gen
Best for
Teams evaluating AI models, assistants and generative workflows — free to start, source available on GitHub.
Known limitations
Teams that need a vendor SLA before adopting a free tool — check the project's support terms first.
Verify current plan terms with the provider.
Evidence summary
Known limitations
Teams that need a vendor SLA before adopting a free tool — check the project's support terms first.
Catalogue confidence
Catalogue data checked Oct 27, 2026.
GitHub-backed record with source-attributed context.
Repository context
Note
GitHub / turboderp/exllamav2
Learn how it works
A guided tour of this tool
A short, animated walkthrough of the architecture, features and full README.
Public record assistant
Ask about ExLlamaV2
Evidence-bound answers from this catalogue record. No workspace data is used.
Sign in to ask Oryxen AI about this record
The database-first brief above stays free for everyone.
Record provenance
What this record is based on.
Oryxen distinguishes catalogue metadata from repository context. These signals describe the directory record and its sources; they do not guarantee the current availability, security, or suitability of an external product.
- Listing status
- Listed in active catalogue
- Freshness
- Catalogue updated Oct 27, 2026
- Source
- GitHub-backed record
- Repository context
- Repository activity not yet retrieved
Key links
Keep researching this tool
Community signal
Practical notes from users.
Feedback is public only after moderation. It is distinct from README-derived project context.
Add your signal
Used this tool?
Sign in to submit feedback for moderation.
Don't miss — compare before you commit
Top 4 alternatives to ExLlamaV2 you should see.
Same category · honest pricing & fit — click any card to compare.