New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
DeepSeek-R1-Distill-Llama-8B
About DeepSeek-R1-Distill-Llama-8B
DeepSeek-R1-Distill-Llama-8B is an AI model developed by DeepSeek, in the language category, released in 2025, made available as an open-weights model with 8B params.
On this page you'll find DeepSeek-R1-Distill-Llama-8B's full specifications, including 17 benchmark results. Review provider pricing and benchmark scores below, or compare DeepSeek-R1-Distill-Llama-8B head-to-head with other language models.
Links
Run DeepSeek-R1-Distill-Llama-8B locally — what to buy
Share this build ↗Sized to what DeepSeek-R1-Distill-Llama-8B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.
Software support
✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.
Community
No reports yet. Own this model on some hardware? Be the first to confirm it runs.
No comments yet. Start the discussion.
DeepSeek-R1-Distill-Llama-8B benchmark scores▶
| Benchmark | Category | Score | Variant |
|---|---|---|---|
| HumanEval | code | 67.54% | cited-granite-3-2 |
| HumanEval+ | code | 62.91% | cited-granite-3-2 |
| LiveCodeBench | code | 39.6% | pass@1-cited-exaone |
| AlpacaEval 2 | general | 21.85% | cited-granite-3-2 |
| ArenaHard | general | 17.17% | cited-granite-3-2 |
| IFEval | general | 66.5% | cited-granite-3-2 |
| MMLU | general | 45.8% | cited-granite-3-2 |
| AIME 2024 | math | 80% | cons@64-cited-exaone |
| AIME 2024 | math | 50.4% | pass@1-cited-exaone |
| AIME 2025 | math | 53.3% | cons@64-cited-exaone |
| AIME 2025 | math | 33.6% | pass@1-cited-exaone |
| GSM8K | math | 72.18% | cited-granite-3-2 |
| MATH-500 | math | 89.1% | pass@1-cited-exaone |
| BIG-Bench Hard | reasoning | 65.71% | cited-granite-3-2 |
| DROP | reasoning | 44.46% | cited-granite-3-2 |
| GPQA Diamond | reasoning | 49% | pass@1-cited-exaone |
| TruthfulQA | safety | 47.43% | cited-granite-3-2 |
More models like DeepSeek-R1-Distill-Llama-8B
Frequently asked questions
What is DeepSeek-R1-Distill-Llama-8B? ▶
DeepSeek-R1-Distill-Llama-8B is an AI model developed by DeepSeek, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.
Who created DeepSeek-R1-Distill-Llama-8B? ▶
DeepSeek-R1-Distill-Llama-8B was developed by DeepSeek and released in 2025.
Is DeepSeek-R1-Distill-Llama-8B open source or proprietary? ▶
DeepSeek-R1-Distill-Llama-8B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.
How much does DeepSeek-R1-Distill-Llama-8B cost? ▶
Pricing for DeepSeek-R1-Distill-Llama-8B depends on the provider. See the providers table on this page for the latest API rates.
How does DeepSeek-R1-Distill-Llama-8B perform on benchmarks? ▶
DeepSeek-R1-Distill-Llama-8B is benchmarked across 17 evaluations on GenAIList, including HumanEval (67.54%). See the full benchmark table below and compare it with other models.
No videos yet. Know a good one? Add it below.
Know a great video about DeepSeek-R1-Distill-Llama-8B?
Add YouTube Video
Add Tweet/Discussion
Report an Issue
Help us maintain accurate information in our database.
Suggest an Edit
Tell us what needs to be changed or corrected for