What LLMs Can the RTX 3080 12GB Run?
The RTX 3080 12GB has 12 GB of VRAM and 912 GB/s of bandwidth. It runs 25 of 58 models fully at Q4_K_M with 8K context, up to Qwen 3 14B, and generates about 106 tokens/s on an 8B model.
25 of 58 models fit
RTX 3080 12GB (12.0 GB) at Q4_K_M with 8K context. Largest that fits fully: Qwen 3 14B.
| Model | Needs | Status | Speed | Best quant that fits |
|---|---|---|---|---|
| Qwen 2.5 14B | 10.7 GB | Fits | ~59 tok/s | Q4_K_M |
| DeepSeek R1 Distill Qwen 14B | 10.7 GB | Fits | ~59 tok/s | Q4_K_M |
| Phi-4 14B | 10.6 GB | Fits | ~59 tok/s | Q4_K_M |
| Qwen 3 14B | 10.5 GB | Fits | ~60 tok/s | Q4_K_M |
| Ministral 3 14B | 9.7 GB | Fits | ~65 tok/s | Q5_K_M |
| Mistral Nemo 12B | 9.0 GB | Fits | ~71 tok/s | Q5_K_M |
| Gemma 3 12B | 8.8 GB | Fits | ~72 tok/s | Q6_K |
| Ministral 3 8B | 6.7 GB | Fits | ~100 tok/s | Q8_0 |
| Qwen 3 8B | 6.6 GB | Fits | ~103 tok/s | Q8_0 |
| Qwen 3.5 9B | 6.4 GB | Fits | ~102 tok/s | Q8_0 |
| Llama 3.1 8B | 6.3 GB | Fits | ~106 tok/s | Q8_0 |
| DeepSeek R1 Distill Llama 8B | 6.3 GB | Fits | ~106 tok/s | Q8_0 |
| Mistral 7B v0.3 | 5.7 GB | Fits | ~116 tok/s | Q8_0 |
| Gemma 4 E4B | 5.7 GB | Fits | ~114 tok/s | Q8_0 |
| Qwen 2.5 7B | 5.6 GB | Fits | ~118 tok/s | Q8_0 |
| DeepSeek R1 Distill Qwen 7B | 5.6 GB | Fits | ~118 tok/s | Q8_0 |
| Qwen 3 4B | 4.2 GB | Fits | ~182 tok/s | FP16 / BF16 |
| Phi-4 Mini | 4.1 GB | Fits | ~194 tok/s | FP16 / BF16 |
| Gemma 4 E2B | 4.0 GB | Fits | ~178 tok/s | FP16 / BF16 |
| Gemma 3 4B | 3.7 GB | Fits | ~197 tok/s | FP16 / BF16 |
| Qwen 3.5 4B | 3.7 GB | Fits | ~203 tok/s | FP16 / BF16 |
| Ministral 3 3B | 3.5 GB | Fits | ~222 tok/s | FP16 / BF16 |
| Llama 3.2 3B | 3.5 GB | Fits | ~230 tok/s | FP16 / BF16 |
| Llama 3.2 1B | 1.7 GB | Fits | ~604 tok/s | FP16 / BF16 |
| Gemma 3 1B | 1.6 GB | Fits | ~752 tok/s | FP16 / BF16 |
| Mixtral 8x7B | 28.0 GB | 40% on GPU | ~7.8 tok/s | – |
| Qwen 2.5 32B | 21.4 GB | 53% on GPU | ~3.9 tok/s | – |
| Qwen 2.5 Coder 32B | 21.4 GB | 53% on GPU | ~3.9 tok/s | – |
| DeepSeek R1 Distill Qwen 32B | 21.4 GB | 53% on GPU | ~3.9 tok/s | – |
| Qwen 3 32B | 21.4 GB | 53% on GPU | ~3.9 tok/s | – |
| Qwen 3.5 35B-A3B | 21.0 GB | 54% on GPU | ~36 tok/s | – |
| Qwen 3.6 35B-A3B | 21.0 GB | 54% on GPU | ~36 tok/s | – |
| Gemma 4 31B | 19.8 GB | 57% on GPU | ~4.5 tok/s | – |
| Qwen 3 30B-A3B | 18.8 GB | 60% on GPU | ~33 tok/s | – |
| Qwen3-Coder 30B-A3B | 18.8 GB | 60% on GPU | ~33 tok/s | – |
| Gemma 3 27B | 17.6 GB | 64% on GPU | ~6.0 tok/s | – |
| Qwen 3.5 27B | 16.9 GB | 67% on GPU | ~6.6 tok/s | Q2_K |
| Qwen 3.6 27B | 16.9 GB | 67% on GPU | ~6.6 tok/s | Q2_K |
| Qwen 3.8 27B | 16.9 GB | 67% on GPU | ~6.6 tok/s | Q2_K |
| Mistral Small 3.1 24B | 15.6 GB | 72% on GPU | ~8.3 tok/s | Q2_K |
| Gemma 4 26B-A4B | 15.6 GB | 72% on GPU | ~43 tok/s | Q2_K |
| gpt-oss-20b | 12.9 GB | 87% on GPU | ~79 tok/s | Q3_K_M |
| Kimi K2.6 | 566 GB | Too small | – | – |
| DeepSeek R1 671B | 380 GB | Too small | – | – |
| Llama 3.1 405B | 234 GB | Too small | – | – |
| Qwen 3.5 397B-A17B | 226 GB | Too small | – | – |
| DeepSeek V4 Flash | 161 GB | Too small | – | – |
| Qwen 3 235B-A22B | 135 GB | Too small | – | – |
| MiniMax-M2 | 133 GB | Too small | – | – |
| Qwen 3.5 122B-A10B | 70.2 GB | Too small | – | – |
| Mistral Small 4 119B | 68.2 GB | Too small | – | – |
| gpt-oss-120b | 67.2 GB | Too small | – | – |
| Llama 4 Scout | 64.0 GB | Too small | – | – |
| GLM-4.5-Air | 62.1 GB | Too small | – | – |
| Qwen3-Next 80B-A3B | 46.3 GB | Too small | – | – |
| Qwen 2.5 72B | 44.5 GB | Too small | – | – |
| Llama 3.3 70B | 43.2 GB | Too small | – | – |
| DeepSeek R1 Distill Llama 70B | 43.2 GB | Too small | – | – |
RTX 3080 12GB for local AI
The 12 GB refresh of the 3080 with a wider memory bus. It fits the same models as an RTX 3060 12GB but generates tokens about 2.5 times faster.
Among the 10 devices we track with about 12 GB of usable memory, the RTX 3080 12GB is the fastest at generating text, because generation speed follows memory bandwidth. Others in the same class: RTX 5070 12GB, RTX 4070 12GB, RTX 4070 Super 12GB, RTX 4070 Ti 12GB. They all hold the same models; the faster ones simply answer sooner.
Our picks for the RTX 3080 12GB
The model we would run first for each job, chosen from our recommendations by what fits fully with an 8K context. "Best quant" is the highest quality that fits; "max context" is at Q4_K_M or the native format.
| Task | Model | Best quant | Max context | Speed |
|---|---|---|---|---|
| Best all-rounder | Qwen 3 14B | Q4_K_M | 13K | ~60 tok/s |
| Coding | Qwen 3 14B | Q4_K_M | 13K | ~60 tok/s |
| Fastest replies | Qwen 3.5 4B | FP16 / BF16 | 251K | ~203 tok/s |
| Long documents (64K+) | Qwen 3.5 9B | Q8_0 | 164K | ~102 tok/s |
| Images in, text out | Ministral 3 14B | Q5_K_M | 18K | ~65 tok/s |
| Image generation | FLUX.1 [dev] | GGUF Q6_K | – | – |
| Spec | Value |
|---|---|
| Memory | 12 GB |
| Memory bandwidth | 912 GB/s |
| Architecture | Ampere |
| Released | 2022-01 |
| Llama 3.1 8B Q4_K_M speed | ~106 tok/s |
| Largest model that fits | Qwen 3 14B |
Image and video models on the RTX 3080 12GB
Peak VRAM with model swapping (ComfyUI default on smaller cards).
| Model | FP8 | FP8 fit | GGUF Q4 | Q4 fit |
|---|---|---|---|---|
| Stable Diffusion 1.5 | 1.8 GB | Fits | 1.7 GB | Fits |
| SDXL 1.0 | 4.1 GB | Fits | 4.1 GB | Fits |
| Stable Diffusion 3.5 Medium | 6.4 GB | Fits | 6.4 GB | Fits |
| Stable Diffusion 3.5 Large | 8.6 GB | Fits | 6.4 GB | Fits |
| FLUX.1 [dev] | 12.1 GB | 93% on GPU | 7.3 GB | Fits |
| FLUX.1 [schnell] | 12.1 GB | 93% on GPU | 7.3 GB | Fits |
| Qwen-Image | 20.4 GB | 55% on GPU | 12.3 GB | 92% on GPU |
| Wan 2.2 A14B (T2V / I2V) | 18.8 GB | 60% on GPU | 13.2 GB | 85% on GPU |
| Wan 2.2 TI2V 5B | 8.0 GB | Fits | 6.5 GB | Fits |
| HunyuanVideo | 18.3 GB | 61% on GPU | 13.1 GB | 86% on GPU |
| FLUX.1 Kontext [dev] | 12.3 GB | 92% on GPU | 7.5 GB | Fits |
| FLUX.2 [dev] | 31.0 GB | 36% on GPU | 23.6 GB | 48% on GPU |
| Z-Image Turbo | 6.8 GB | Fits | 4.9 GB | Fits |
| Qwen-Image-Edit 2509 | 20.5 GB | 55% on GPU | 12.4 GB | 91% on GPU |
| LTX-2 | 19.2 GB | 59% on GPU | 12.6 GB | 90% on GPU |
Upgrade path
The next step up is the RTX 4060 Ti 16GB with 16 GB.
RTX 3080 12GB for LLMs: common questions
Can the RTX 3080 12GB run Llama 3.3 70B?
No. It needs about 43.2 GB at Q4_K_M, far more than the 12.0 GB available.
Can the RTX 3080 12GB run Qwen 3 32B?
Only partly. It needs about 21.4 GB at Q4_K_M, so about 53% fits in VRAM and the rest runs from system RAM, which is slow.
Can the RTX 3080 12GB run Qwen 3 14B?
Yes. Qwen 3 14B needs about 10.5 GB at Q4_K_M with 8K context, and the best quality that fits is Q4_K_M.
How fast is the RTX 3080 12GB for LLMs?
About 106 tokens per second for an 8B model at Q4_K_M, based on its 912 GB/s memory bandwidth. Larger models scale down roughly in proportion to their size.