HARDWARE / VRAM

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.

Źródło pierwotne

Consumer Ada GPU24 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 Swobodnie and keep context modest.

02 / DEFAULT RUNTIME

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.

Otwórz przewodnik

03 / MODEL ENVELOPE

Reprezentatywne modele open-weight

Nex AGI

Nex-N2.5-mini

English

35BQ4 estimated budget

Szacowana pamięć: ~21 GB
Kontekst: 262,144 (config max_position_embeddings)

Alibaba Qwen

Qwen3 30B-A3B

30B3B active · GGUF Q4 MoE

Szacowana pamięć: ~22.5 GB
Kontekst: 32K+

Alibaba Qwen

Qwen3.6 27B

27BQ4 / NVFP4 estimate

Szacowana pamięć: ~18.5 GB
Kontekst: 262K native

Alibaba Qwen

Qwen3.8 27B

27BQ4 estimate

Szacowana pamięć: ~19.5 GB
Kontekst: 262K native

Google

Gemma 3 27B

27BINT4

Szacowana pamięć: ~20.5 GB
Kontekst: 128K

Mistral AI

Devstral Small 2 24B

24BGGUF Q4 / BF16

Szacowana pamięć: ~18.5 GB
Kontekst: 256K

Uwaga

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 (Na styk), Qwen3 30B-A3B (Na styk), Qwen3.6 27B (Na styk), Qwen3.8 27B (Na styk), Gemma 3 27B (Na styk), Devstral Small 2 24B (Na styk).