Written by Jakub Rusinowski · Last updated September 6, 2026
Best all-round pick: Gemma 4 27B ⭐
The AMD Radeon RX 7900 XT has 20 GB of VRAM, of which about 20 GB is available to a model. The largest model it can hold is Gemma 4 31B (31B, 19.5 GB at Q4_K_M).
| Model | Score | Memory at Q4_K_M | Context | Licence |
|---|---|---|---|---|
| Gemma 4 27B ⭐ | 97.4 | 17.1 GB | 125K | Gemma License (commercial OK) |
| Mistral Small 3.1 24B | 95.9 | 15 GB | 125K | Apache 2.0 |
| Qwen3.8 27B | 95.9 | 17.6 GB | 256K | Apache-2.0 |
| Gemma 4 31B | 94.8 | 19.5 GB | 250K | Apache-2.0 |
| Qwen 3 30B-A3B (MoE) | 94 | 19.2 GB | 125K | Apache 2.0 |
| Gemma 3 27B Instruct | 93.8 | 17.1 GB | 128K | Gemma |
| Workload | Recommended on this GPU |
|---|---|
| Coding | Gemma 4 31B (97.4) Gemma 4 27B ⭐ (96.8) Qwen 3.6 27B (96.8) |
| General assistant | Gemma 4 27B ⭐ (97.4) Mistral Small 3.1 24B (95.9) Qwen3.8 27B (95.9) |
| Reasoning | Gemma 4 27B ⭐ (100) Gemma 4 31B (97.8) Qwen 3.6 27B (96.5) |
| RAG | Gemma 4 31B (97.5) Qwen 3.6 27B (96.7) Qwen3.8 27B (95.9) |
| Agents | Ternary Bonsai 27B (94) GLM-4.7-Flash 30B-A3B (90.4) Nemotron 3 Nano Omni 30B-A3B (88.7) |
| Vision | Gemma 4 31B (97.8) Gemma 4 27B ⭐ (96.8) Qwen3.8 27B (95.7) |
These models are strong picks generally but exceed the 20 GB this card makes available.
| Model | Needs at Q4_K_M | Short by |
|---|---|---|
| Qwen 3.7 35B-A3B | 22 GB | ~2 GB |
| Qwen 3.6 35B-A3B | 22 GB | ~2 GB |
| Qwen 3.5 35B-A3B | 22 GB | ~2 GB |
| Command R (35B) | 22 GB | ~2 GB |
Gemma 4 27B ⭐ is the strongest all-round pick that fits its 20 GB.
Gemma 4 31B — 31B parameters, needing 19.5 GB at Q4_K_M.
About 20 GB of its 20 GB, before the desktop and runtime overhead are accounted for.