Best LLMs for 16 GB
Pick your memory. We rank every catalogued model that fits at its recommended quantization, by task, and show what the next tier up unlocks.
Written by Jakub Rusinowski · Last updated
Best at 16 GB, by task
Score is the task-specific quality score on a 0–100 scale; speed is estimated for the RX 9060 XT 16GB.
The strongest that fit
Top 15, by logic and coding
| Model | Memory · marker = 16 GB | VRAM | Speed on RX 9060 XT 16GB (est.) | Score |
|---|---|---|---|---|
| Qwen 2.5 14B Instruct Qwen 2.5 Family · Q4_K_M | 8.5 GB | ~22 tok/s | 95 | |
| Qwen 3 14B Qwen 3 · Q4_K_M | 8.9 GB | ~22 tok/s | 94 | |
| Codestral 22B Codestral · Q4_K_M | 13.4 GB | ~15 tok/s | 93 | |
| DeepSeek R1 Distill Qwen 14B DeepSeek R1 · Q4_K_M | 8.5 GB | ~23 tok/s | 92 | |
| Phi-4 (14B) Phi-4 Family · Q4_K_M | 8.5 GB | ~22 tok/s | 92 | |
| Mistral Small 3.1 24B Mistral Small 3.1 · Q4_K_M | 14.2 GB | ~14 tok/s | 91 | |
| InternLM 3 20B Instruct InternLM 3 · Q4_K_M | 12.1 GB | ~16 tok/s | 91 | |
| Mistral Small 3 (24B) Mistral Family · Q4_K_M | 14.5 GB | — | 90 | |
| Granite 3.0 8B Instruct Granite 3.0 · Q4_K_M | 4.8 GB | ~36 tok/s | 90 | |
| Ternary Bonsai 27B Bonsai 27B · Ternary (1.58-bit, ~1.71 bpw) | 5.8 GB | ~30 tok/s | 90 | |
| Qwen 2.5 7B Instruct Qwen 2.5 Family · Q4_K_M | 4.6 GB | ~40 tok/s | 89 | |
| Qwen 3 8B Qwen 3 · Q4_K_M | 5 GB | ~35 tok/s | 89 | |
| DeepSeek R1 Distill Llama 8B DeepSeek R1 · Q4_K_M | 4.8 GB | ~36 tok/s | 89 | |
| Mistral NeMo 12B Mistral Family · Q4_K_M | 7.2 GB | ~26 tok/s | 88 | |
| Devstral Small 2 24B Devstral · Q4_K_M | 14.5 GB | ~14 tok/s | 87 |
What 20 GB unlocks
The strongest models that need the next tier up.
FAQ
What LLMs run well with 16 GB VRAM?
Qwen 2.5 Family, Qwen 3, Codestral, DeepSeek R1, Phi-4 Family all fit in 16 GB VRAM.
Which GPUs have 16 GB VRAM?
AMD Radeon RX 9060 XT 16GB, Intel Arc Pro B50, NVIDIA GeForce RTX 5060 Ti 16GB, NVIDIA GeForce RTX 4060 Ti 16GB.
All tiers at a glance
| Memory | Models fit | Best overall | Largest that fits |
|---|---|---|---|
| 4 GB | 32 | Gemma 3 4B Instruct | Gemma 3 4B Instruct · 2.4 GB |
| 6 GB | 56 | Granite 3.0 8B Instruct | Qwen 2.5 VL 7B Instruct · 5 GB |
| 8 GB | 71 | Granite 3.0 8B Instruct | Falcon 3 10B Instruct · 6.2 GB |
| 10 GB | 83 | Qwen 2.5 14B Instruct | Qwen 3 14B · 8.9 GB |
| 12 GB | 85 | Qwen 2.5 14B Instruct | StarCoder 2 15B · 9.4 GB |
| 16 GB | 95 | Qwen 2.5 14B Instruct | Mistral Small 3 (24B) · 14.5 GB |
| 20 GB | 111 | Qwen 2.5 14B Instruct | Gemma 4 31B · 18.7 GB |
| 24 GB | 131 | Qwen 2.5 Coder 32B | Qwen 3.6 35B-A3B · 21.1 GB |
| 32 GB | 132 | Qwen 2.5 Coder 32B | Qwen 3.6 35B-A3B · 21.1 GB |
| 48 GB | 138 | Qwen 2.5 72B Instruct | Qwen 2.5 VL 72B Instruct · 44.3 GB |
| 64 GB | 143 | Qwen 2.5 72B Instruct | Qwen3-Coder-Next (80B-A3B MoE) · 48.3 GB |
| 80 GB | 152 | Qwen 2.5 72B Instruct | Qwen 3.5 122B-A10B · 73.7 GB |
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.
Can-I-Run Pages Near 16 GB
- DeepSeek R1 on NVIDIA GeForce RTX 5080
- DeepSeek R1 on NVIDIA GeForce RTX 5070 Ti
- DeepSeek R1 on NVIDIA GeForce RTX 5060 Ti 16GB
- DeepSeek R1 on NVIDIA GeForce RTX 4080 Super
- DeepSeek R1 on NVIDIA GeForce RTX 4080
- DeepSeek R1 on NVIDIA GeForce RTX 4070 Ti Super
- DeepSeek R1 on NVIDIA GeForce RTX 4060 Ti 16GB
- DeepSeek R1 on AMD Radeon RX 7800 XT