Darwin-9B-NEG
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve ansulev/Darwin-9B-NEGNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Darwin-9B-NEG
Darwin-9B-NEG is a 9.7B-parameter apache-2.0 model from ansulev. At Q4_K_M it needs roughly 6 GB of VRAM, placing it in the 8–12 GB GPU hardware tier.
Specifications
| Spec | Value |
|---|---|
| Parameters | 9.7B |
| Context length | 262K tokens |
| License | apache-2.0 |
| Modalities | text, vision |
| Released | 2026-05-18 |
| Weights | ansulev/Darwin-9B-NEG |
VRAM requirements
| Quant | VRAM | Runs on |
|---|---|---|
| Q4_K_M | ~6 GB | RTX 4060, RTX 3060 8GB |
| Q5_K_M | ~7 GB | RTX 4060, RTX 3060 8GB |
| Q8_0 | ~10 GB | RTX 3060 12GB, RTX 4070 |
| FP16 | ~19 GB | RTX 3090, RTX 4090 |
VRAM is estimated from parameter count; MoE models still need all weights resident.
How to run
vLLM:
vllm serve ansulev/Darwin-9B-NEGPopularity
Darwin-9B-NEG has 552,250 downloads in the last month on HuggingFace and 15 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Darwin-9B-NEG need?
Darwin-9B-NEG with 9.7B parameters needs approximately 6 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Darwin-9B-NEG better than other ansulev models?
Darwin-9B-NEG has 9.7B parameters with 262,144 context - a strong choice for general use.
What license is Darwin-9B-NEG under?
Darwin-9B-NEG is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Darwin-9B-NEG well?
With 9.7B parameters, Darwin-9B-NEG requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Darwin-9B-NEG?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~7 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Darwin-9B-NEG's context window handle?
Darwin-9B-NEG supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Darwin-9B-NEG?
Darwin-9B-NEG competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec
Comments coming soon
Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.