Best LLMs and AI models for 16 GB VRAM (2026)
2 439 open-weight models fit fully in 16 GB of GPU memory at their recommended quantisation. Each section puts the strongest model that still fits comfortably first, with the best quantisation and an estimated generation speed.
A GPU with 16 GB of VRAM leaves 16 GB usable for model weights, enough to run several open-weight language models locally. Models in the 8B to 12B range fit, and so does gpt-oss-20b at 20.9B parameters. Popular picks include Llama-3.1-8B-Instruct from Meta, Qwen3-8B from Qwen, and gemma-4-12B-it from Google.
Best chat models for 16 GB
All 921 that fit →| # | Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|---|
| 1 | 20.9BA4.2B | Q8_0 | ≈13 GBFits in memory | ~55 tok/s | |
| 2 | 14.8B | Q6_K | ≈14 GBFits in memory | ~20 tok/s | |
| 3 | 8.2B | Q8_0 | ≈10 GBFits in memory | ~28 tok/s | |
| 4 | 14.8B | Q6_K | ≈14 GBFits in memory | ~20 tok/s | |
| 5 | 14.7B | Q6_K | ≈14 GBFits in memory | ~20 tok/s | |
| 6 | 20.2BA1.5B | Q5_K_M | ≈15 GBFits in memory | ~232 tok/s | |
| 7 | 9.7B | Q8_0 | ≈11 GBFits in memory | ~24 tok/s | |
| 8 | 7.9BA1.4B | Q8_0 | ≈10 GBFits in memory | ~168 tok/s |
Best code models for 16 GB
All 79 that fit →| # | Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|---|
| 1 | 12.1BA2.5B | Q8_0 | ≈14 GBFits in memory | ~93 tok/s | |
| 2 | 14.8B | Q6_K | ≈14 GBFits in memory | ~20 tok/s | |
| 3 | 12.1BA2.5B | Q8_0 | ≈14 GBFits in memory | ~93 tok/s | |
| 4 | 15.7BA2.7B | Q5_K_M | ≈15 GBFits in memory | ~130 tok/s | |
| 5 | 16B | Q6_K | ≈14 GBFits in memory | ~19 tok/s | |
| 6 | 9.4B | Q8_0 | ≈11 GBFits in memory | ~25 tok/s | |
| 7 | 15.8B | Q6_K | ≈15 GBFits in memory | ~19 tok/s | |
| 8 | 7.6B | Q8_0 | ≈8.9 GBFits in memory | ~30 tok/s |
Best reasoning models for 16 GB
All 51 that fit →| # | Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|---|
| 1 | 14.8B | Q6_K | ≈14 GBFits in memory | ~20 tok/s | |
| 2 | 14.7B | Q6_K | ≈14 GBFits in memory | ~20 tok/s | |
| 3 | 14.7B | Q6_K | ≈14 GBFits in memory | ~20 tok/s | |
| 4 | 15.9BA3B | Q5_K_M | ≈14 GBFits in memory | ~115 tok/s | |
| 5 | 21.8BA3B | Q4_K_M | ≈14 GBFits in memory | ~135 tok/s | |
| 6 | 14.8B | Q6_K | ≈14 GBFits in memory | ~20 tok/s | |
| 7 | 7.3B | Q8_0 | ≈12 GBFits in memory | ~32 tok/s | |
| 8 | 16.3BA1.4B | Q6_K | ≈14 GBFits in memory | ~209 tok/s |
Best vision models for 16 GB
All 336 that fit →| # | Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|---|
| 1 | 9.7B | Q8_0 | ≈11 GBFits in memory | ~24 tok/s | |
| 2 | 19.4BA3B | Q4_K_M | ≈13 GBFits in memory | ~135 tok/s | |
| 3 | 16.4BA3B | Q5_K_M | ≈15 GBFits in memory | ~115 tok/s | |
| 4 | 13.2B | Q6_K | ≈13 GBFits in memory | ~23 tok/s | |
| 5 | 9.4B | Q8_0 | ≈11 GBFits in memory | ~25 tok/s | |
| 6 | 16.4BA3B | Q5_K_M | ≈14 GBFits in memory | ~115 tok/s | |
| 7 | 8.8B | Q8_0 | ≈10 GBFits in memory | ~26 tok/s | |
| 8 | 12.2B | Q6_K | ≈13 GBFits in memory | ~25 tok/s |
Best image gen models for 16 GB
All 112 that fit →| # | Model | Params | Best quant | Memory |
|---|---|---|---|---|
| 1 | 7.1B | Q8_0 | ≈8.9 GBFits in memory | |
| 2 | 7.1B | Q8_0 | ≈8.9 GBFits in memory | |
| 3 | 6.2B | FP16 / BF16 | ≈14 GBFits in memory | |
| 4 | 5.1B | FP16 / BF16 | ≈12 GBFits in memory | |
| 5 | 12.8B | Q4_K_M | ≈9.2 GBFits in memory | |
| 6 | 5.1B | FP16 / BF16 | ≈12 GBFits in memory | |
| 7 | 6.2B | FP16 / BF16 | ≈14 GBFits in memory | |
| 8 | 12.8B | Q4_K_M | ≈9.2 GBFits in memory |
Best STT models for 16 GB
All 100 that fit →| # | Model | Params | Best quant | Memory |
|---|---|---|---|---|
| 1 | 2.1B | FP16 / BF16 | ≈5.1 GBFits in memory | |
| 2 | 2.3B | FP16 / BF16 | ≈5.8 GBFits in memory | |
| 3 | 8.7B | Q8_0 | ≈11 GBFits in memory | |
| 4 | 8.7B | Q8_0 | ≈11 GBFits in memory | |
| 5 | 4.4B | FP16 / BF16 | ≈10 GBFits in memory | |
| 6 | 2.3B | FP16 / BF16 | ≈5.7 GBFits in memory | |
| 7 | 627M | FP16 / BF16 | ≈1.9 GBFits in memory | |
| 8 | 909M | FP16 / BF16 | ≈2.5 GBFits in memory |
Best TTS models for 16 GB
All 111 that fit →| # | Model | Params | Best quant | Memory |
|---|---|---|---|---|
| 1 | 3.6B | FP16 / BF16 | ≈8.6 GBFits in memory | |
| 2 | 3.5B | FP16 / BF16 | ≈8.3 GBFits in memory | |
| 3 | 2.3B | FP16 / BF16 | ≈5.6 GBFits in memory | |
| 4 | 613M | FP16 / BF16 | ≈1.9 GBFits in memory | |
| 5 | 1.9B | FP16 / BF16 | ≈4.8 GBFits in memory | |
| 6 | 915M | FP16 / BF16 | ≈2.5 GBFits in memory | |
| 7 | 1.5B | FP16 / BF16 | ≈3.8 GBFits in memory | |
| 8 | 4.6B | FP16 / BF16 | ≈11 GBFits in memory |
Best embedding models for 16 GB
All 241 that fit →| # | Model | Params | Best quant | Memory |
|---|---|---|---|---|
| 1 | 744M | FP16 / BF16 | ≈2.2 GBFits in memory | |
| 2 | 7.6B | Q8_0 | ≈9.5 GBFits in memory | |
| 3 | 303M | FP16 / BF16 | ≈1.2 GBFits in memory | |
| 4 | 596M | FP16 / BF16 | ≈1.8 GBFits in memory | |
| 5 | 4B | FP16 / BF16 | ≈9.5 GBFits in memory | |
| 6 | 8B | Q8_0 | ≈9.9 GBFits in memory | |
| 7 | 1.1B | FP16 / BF16 | ≈3.0 GBFits in memory | |
| 8 | 8.1B | Q8_0 | ≈10 GBFits in memory |
GPUs with 16–18 GB 57
Frequently asked questions
- What is the best LLM for 16 GB of VRAM?
- Our top chat pick for 16 GB is gpt-oss-20b (openai) at Q8_0, needing about 12.72 GB, at roughly 55 tokens/s. The ranking favours the strongest model that still fits comfortably, then benchmarks, popularity and release date.
- What is the best coding model for 16 GB of VRAM?
- Mellum2.1-12B-A2.5B-Thinking (JetBrains) at Q8_0, needing about 13.58 GB, at roughly 93 tokens/s.
- How big a model fits in 16 GB of VRAM?
- Dense LLMs up to about 22.1B parameters fit fully in 16 GB at Q4_K_M or better, with an 8K-token context. Longer contexts need more memory for the KV cache.
- How many open-weight models run on 16 GB of VRAM?
- 2439 open-weight models on this site fit fully in 16 GB at their recommended quantisation, across 19 categories (chat, code, vision, image generation, speech and more).
- How fast are models on 16 GB of VRAM?
- Token generation is limited by memory bandwidth. The speeds on this page assume about 448 GB/s, typical for 16 GB cards; a faster or slower card scales roughly in proportion. Open your GPU’s page for estimates with its own bandwidth.
- Which GPUs have 16 GB of VRAM?
- Among others: GeForce RTX 5060 Ti 16GB, GeForce RTX 5070 Ti, GeForce RTX 5080, Radeon RX 9060 XT 16GB, Radeon RX 9070 XT, Apple M4 (16 GB). Each GPU page lists what fits and how fast it runs.
- What if a model doesn’t fit in 16 GB?
- llama.cpp, Ollama and LM Studio can offload part of an LLM to system RAM. It runs, but generation slows down a lot because RAM is far slower than VRAM. The 20 GB page shows what one more step of memory buys.
Memory figures are estimates: weights at the given quantisation plus an 8K-token KV cache and runtime overhead. On Macs and other unified-memory machines only part of the memory is available to the GPU, see the Apple Silicon pages.