GeForce RTX 4090 · 24 GB
A 27B Q4 checkpoint can be a tight fit. Leave room for runtime overhead and KV cache instead of filling every gigabyte with weights.
PrimärquelleNex-N2.5-mini
The highest listed result may be a tight or offloaded fit. For daily use, prefer the first result marked Bequem and keep context modest.
llama.cpp
GGUF models, CPU/GPU offload, embedded and unusual hardware. New architectures may require a recent build. Backend availability does not imply equal performance. Since v0.7.0 (2026-10-15) llama-server listens on port 9931 by default instead of 8080; the example commands pin that port explicitly. Older builds accept the same --port flag but default to 8080.
Leitfaden öffnenRepräsentative Open-Weight-Modelle
Nex-N2.5-mini
English- Geschätzter Speicher
- ~21 GB
- Kontext
- 262,144 (config max_position_embeddings)
Qwen3 30B-A3B
- Geschätzter Speicher
- ~22.5 GB
- Kontext
- 32K+
Qwen3.6 27B
- Geschätzter Speicher
- ~18.5 GB
- Kontext
- 262K native
Qwen3.8 27B
- Geschätzter Speicher
- ~19.5 GB
- Kontext
- 262K native
Gemma 3 27B
- Geschätzter Speicher
- ~20.5 GB
- Kontext
- 128K
Devstral Small 2 24B
- Geschätzter Speicher
- ~18.5 GB
- Kontext
- 256K
Fit is based on estimated total model memory. Driver support, KV cache, multimodal projectors, concurrency, and desktop applications can all reduce available headroom. Current fit: Nex-N2.5-mini (Knapp), Qwen3 30B-A3B (Knapp), Qwen3.6 27B (Knapp), Qwen3.8 27B (Knapp), Gemma 3 27B (Knapp), Devstral Small 2 24B (Knapp).