作者： Jakub Rusinowski · 最后更新： 2026年9月6日
These are the strongest local models that fit entirely in 20 GB of VRAM, ranked by capability, with the quantization level and estimated tokens/sec needed to fit.
| Qwen 2.5 Family — Qwen 2.5 14B Instruct | Q4_K_M · 8.4525 GB · ~47 tok/s on AMD Radeon RX 7900 XT |
| Gemma 4 (Legacy Listing — Unverified) — Gemma 4 27B ⭐ | Q4_K_M · 16.30125 GB · ~27 tok/s on AMD Radeon RX 7900 XT |
| Qwen 3 — Qwen 3 14B | Q4_K_M · 8.935500000000001 GB · ~46 tok/s on AMD Radeon RX 7900 XT |
| Codestral — Codestral 22B | Q4_K_M · 13.40325 GB · ~32 tok/s on AMD Radeon RX 7900 XT |
| DeepSeek R1 — DeepSeek R1 Distill Qwen 14B | Q4_K_M · 8.4525 GB · ~48 tok/s on AMD Radeon RX 7900 XT |
| Phi-4 Family — Phi-4 (14B) | Q4_K_M · 8.4525 GB · ~47 tok/s on AMD Radeon RX 7900 XT |
| Gemma 4 — Gemma 4 31B | Q4_K_M · 18.71625 GB |
| Gemma 3 — Gemma 3 27B Instruct | Q4_K_M · 16.30125 GB |
| Mistral Small 3.1 — Mistral Small 3.1 24B | Q4_K_M · 14.248500000000002 GB · ~31 tok/s on AMD Radeon RX 7900 XT |
| Qwen 3.6 — Qwen 3.6 27B | Q4_K_M · 16.78425 GB · ~27 tok/s on AMD Radeon RX 7900 XT |
| InternLM 3 — InternLM 3 20B Instruct | Q4_K_M · 12.075 GB · ~35 tok/s on AMD Radeon RX 7900 XT |
| Qwen3.8 — Qwen3.8 27B | Q4_K_M · 16.772175 GB · ~27 tok/s on AMD Radeon RX 7900 XT |
| Mistral Family — Mistral Small 3 (24B) | Q4_K_M · 14.49 GB · ~30 tok/s on AMD Radeon RX 7900 XT |
| Qwen 3 — Qwen 3 30B-A3B (MoE) | Q4_K_M · 18.414375 GB · ~123 tok/s on AMD Radeon RX 7900 XT |
| Granite 3.0 — Granite 3.0 8B Instruct | Q4_K_M · 4.83 GB · ~71 tok/s on AMD Radeon RX 7900 XT |
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Qwen 2.5 Family, Gemma 4 (Legacy Listing — Unverified), Qwen 3, Codestral, DeepSeek R1 all fit in 20 GB VRAM.
AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, Apple M2, Apple M3.