HARDWARE / VRAM
Workstation · 48 GB
70B Q4 serving begins here, with limited room for cache and concurrency.
RTX 6000 / dual GPU48 GB
01 / PRACTICAL CEILING
Nex-N2.5-mini
The highest listed result may be a tight or offloaded fit. For daily use, prefer the first result marked Rahat and keep context modest.
02 / DEFAULT RUNTIME
vLLM
Linux GPU servers, concurrency and OpenAI-compatible production APIs. CUDA, ROCm and XPU feature coverage differs. Driver, shared-memory and quantization compatibility are version-specific.
Rehberi aç03 / MODEL ENVELOPE
Temsilî açık ağırlıklı modeller
Nex AGI
Nex-N2.5-mini
English35BQ4 estimated budget
- Tahmini bellek
- ~21 GB
- Bağlam
- 262,144 (config max_position_embeddings)
Alibaba Qwen
Qwen3.6 35B-A3B
35B3B active · Q4 / NVFP4 MoE
- Tahmini bellek
- ~25 GB
- Bağlam
- 262K native
Alibaba Qwen
Qwen3 32B
32BGGUF Q4
- Tahmini bellek
- ~24.5 GB
- Bağlam
- 32K+
Alibaba Qwen
Qwen3 30B-A3B
30B3B active · GGUF Q4 MoE
- Tahmini bellek
- ~22.5 GB
- Bağlam
- 32K+
Alibaba Qwen
Qwen3.6 27B
27BQ4 / NVFP4 estimate
- Tahmini bellek
- ~18.5 GB
- Bağlam
- 262K native
Alibaba Qwen
Qwen3.8 27B
27BQ4 estimate
- Tahmini bellek
- ~19.5 GB
- Bağlam
- 262K native
Dikkat
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 (Rahat), Qwen3.6 35B-A3B (Rahat), Qwen3 32B (Rahat), Qwen3 30B-A3B (Rahat), Qwen3.6 27B (Rahat), Qwen3.8 27B (Rahat).