Best LLMs and AI models for 12 GB VRAM (2026)
2 340 open-weight models fit fully in 12 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 12 GB of VRAM has 12 GB usable for models, which covers open-weight models from about 0.8B to 12B parameters. Several popular models fit that budget, including Qwen3-8B from Qwen, Llama-3.1-8B-Instruct from meta-llama and gemma-4-12B-it from google. Smaller options such as Qwen3-0.6B also fit, along with gemma-4-E4B-it and Qwen3.5-9B.
Best chat models for 12 GB
All 874 that fit →| # | Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|---|
| 1 | 8.2B | Q8_0 | ≈10 GBFits in memory | ~27 tok/s | |
| 2 | 14.8B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 3 | 9.7B | Q8_0 | ≈11 GBFits in memory | ~23 tok/s | |
| 4 | 7.9BA1.4B | Q8_0 | ≈10 GBFits in memory | ~162 tok/s | |
| 5 | 14.8B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 6 | 9B | Q8_0 | ≈11 GBFits in memory | ~25 tok/s | |
| 7 | 14.7B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 8 | 8.8B | Q8_0 | ≈11 GBFits in memory | ~25 tok/s |
Best code models for 12 GB
All 74 that fit →| # | Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|---|
| 1 | 12.1BA2.5B | Q5_K_M | ≈11 GBFits in memory | ~134 tok/s | |
| 2 | 12.1BA2.5B | Q6_K | ≈11 GBFits in memory | ~115 tok/s | |
| 3 | 14.8B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 4 | 9.4B | Q8_0 | ≈11 GBFits in memory | ~24 tok/s | |
| 5 | 7.6B | Q8_0 | ≈8.9 GBFits in memory | ~29 tok/s | |
| 6 | 16B | Q4_K_M | ≈11 GBFits in memory | ~25 tok/s | |
| 7 | 14.8B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 8 | 14.8B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s |
Best reasoning models for 12 GB
All 50 that fit →| # | Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|---|
| 1 | 14.8B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 2 | 14.7B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 3 | 14.7B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 4 | 7.3B | Q6_K | ≈10 GBFits in memory | ~40 tok/s | |
| 5 | 8.6B | Q8_0 | ≈10 GBFits in memory | ~26 tok/s | |
| 6 | 14.8B | Q4_K_M | ≈11 GBFits in memory | ~27 tok/s | |
| 7 | 16.3BA1.4B | Q4_K_M | ≈11 GBFits in memory | ~273 tok/s | |
| 8 | 7.6B | Q8_0 | ≈8.9 GBFits in memory | ~29 tok/s |
Best vision models for 12 GB
All 331 that fit →| # | Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|---|
| 1 | 9.7B | Q8_0 | ≈11 GBFits in memory | ~23 tok/s | |
| 2 | 9.4B | Q8_0 | ≈11 GBFits in memory | ~24 tok/s | |
| 3 | 8.8B | Q8_0 | ≈10 GBFits in memory | ~26 tok/s | |
| 4 | 9.7B | Q8_0 | ≈11 GBFits in memory | ~23 tok/s | |
| 5 | 9.4B | Q8_0 | ≈11 GBFits in memory | ~24 tok/s | |
| 6 | 9.4B | Q8_0 | ≈11 GBFits in memory | ~24 tok/s | |
| 7 | 4.7B | Q8_0 | ≈5.9 GBFits in memory | ~48 tok/s | |
| 8 | 9.8B | Q8_0 | ≈11 GBFits in memory | ~23 tok/s |
Best image gen models for 12 GB
All 99 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 | Q8_0 | ≈7.8 GBFits in memory | |
| 4 | 5.1B | Q8_0 | ≈6.5 GBFits in memory | |
| 5 | 5.1B | Q8_0 | ≈6.5 GBFits in memory | |
| 6 | 6.2B | Q8_0 | ≈7.8 GBFits in memory | |
| 7 | 8.1B | Q8_0 | ≈10 GBFits in memory | |
| 8 | 6.2B | Q8_0 | ≈7.8 GBFits in memory |
Best STT models for 12 GB
All 99 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 | 909M | FP16 / BF16 | ≈2.5 GBFits in memory | |
| 8 | 627M | FP16 / BF16 | ≈1.9 GBFits in memory |
Best TTS models for 12 GB
All 109 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 | 1.9B | FP16 / BF16 | ≈4.8 GBFits in memory | |
| 5 | 613M | FP16 / BF16 | ≈1.9 GBFits in memory | |
| 6 | 1.5B | FP16 / BF16 | ≈3.8 GBFits in memory | |
| 7 | 915M | FP16 / BF16 | ≈2.5 GBFits in memory | |
| 8 | 4.6B | FP16 / BF16 | ≈11 GBFits in memory |
Best embedding models for 12 GB
All 238 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 | 8.1B | Q8_0 | ≈10 GBFits in memory | |
| 8 | 1.1B | FP16 / BF16 | ≈3.0 GBFits in memory |
GPUs with 12 GB 32
Frequently asked questions
- What is the best LLM for 12 GB of VRAM?
- Our top chat pick for 12 GB is Qwen3-8B (Qwen) at Q8_0, needing about 10.15 GB, at roughly 27 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 12 GB of VRAM?
- Mellum2.1-12B-A2.5B-Thinking (JetBrains) at Q5_K_M, needing about 10.68 GB, at roughly 134 tokens/s.
- How big a model fits in 12 GB of VRAM?
- Dense LLMs up to about 16B parameters fit fully in 12 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 12 GB of VRAM?
- 2340 open-weight models on this site fit fully in 12 GB at their recommended quantisation, across 19 categories (chat, code, vision, image generation, speech and more).
- How fast are models on 12 GB of VRAM?
- Token generation is limited by memory bandwidth. The speeds on this page assume about 432 GB/s, typical for 12 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 12 GB of VRAM?
- Among others: GeForce RTX 5070, Arc B580, GeForce RTX 4070, GeForce RTX 3060 12GB, Radeon RX 6700 XT, GeForce RTX 5070 Ti Laptop. Each GPU page lists what fits and how fast it runs.
- What if a model doesn’t fit in 12 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 16 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.