Written by Jakub Rusinowski · Last updated July 12, 2026
Best all-round pick: Qwen 3 8B
The NVIDIA GeForce RTX 3080 (10GB) has 10 GB of VRAM, of which about 10 GB is available to a model. The largest model it can hold is Qwen 3 14B (15B, 9.7 GB at Q4_K_M).
| Model | Score | Memory at Q4_K_M | Context | Licence |
|---|---|---|---|---|
| Qwen 3 8B | 95.8 | 5.8 GB | 125K | Apache 2.0 |
| Qwen 3.5 14B | 94.4 | 9.3 GB | 125K | Apache 2.0 |
| Gemma 3 12B Instruct | 93.6 | 8 GB | 128K | Gemma |
| Qwen 3.5 14B | 93.5 | 9.3 GB | 125K | Apache 2.0 |
| GLM-6 9B | 93.3 | 6.2 GB | 125K | MIT |
| GLM-4.7 9B | 93.1 | 6.2 GB | 125K | Apache-2.0 |
| Workload | Recommended on this GPU |
|---|---|
| Coding | Qwen3-Coder 8B (95.9) Qwen 3 14B (95.9) DeepSeek R1 Distill Qwen 14B (94.2) |
| General assistant | Qwen 3 8B (95.8) Qwen 3.5 14B (94.4) Gemma 3 12B Instruct (93.6) |
| Reasoning | Qwen 3 14B (96) DeepSeek R1 Distill Llama 8B (94.5) Qwen 3.5 14B (94) |
| RAG | Qwen 3 14B (84.4) Qwen 2.5 14B Instruct (81.8) Qwen 3.5 14B (81.5) |
| Agents | GLM-6 9B (86.8) GLM-5 9B (85.4) Qwen 3.5 14B (84.6) |
| Vision | Qwen 3.5 14B (95.7) Gemma 4 12B (92.3) Gemma 4 12B (Unified) (92) |
These models are strong picks generally but exceed the 10 GB this card makes available.
| Model | Needs at Q4_K_M | Short by |
|---|---|---|
| Gemma 4 27B ⭐ | 17.2 GB | ~7.2 GB |
| Mistral Small 3.1 24B | 15.1 GB | ~5.1 GB |
| Qwen 3.7 35B-A3B | 22 GB | ~12 GB |
| Gemma 4 31B | 19.6 GB | ~9.6 GB |
Qwen 3 8B is the strongest all-round pick that fits its 10 GB.
Qwen 3 14B — 15B parameters, needing 9.7 GB at Q4_K_M.
About 10 GB of its 10 GB, before the desktop and runtime overhead are accounted for.