What LLMs Can the RTX 3080 10GB Run?
The RTX 3080 10GB has 10 GB of VRAM and 760 GB/s of bandwidth. It runs 21 of 58 models fully at Q4_K_M with 8K context, up to Ministral 3 14B, and generates about 89 tokens/s on an 8B model.
21 of 58 models fit
RTX 3080 10GB (10.0 GB) at Q4_K_M with 8K context. Largest that fits fully: Ministral 3 14B.
| Model | Needs | Status | Speed | Best quant that fits |
|---|---|---|---|---|
| Mistral Nemo 12B | 9.0 GB | Fits | ~60 tok/s | Q4_K_M |
| Gemma 3 12B | 8.8 GB | Fits | ~60 tok/s | Q4_K_M |
| Ministral 3 8B | 6.7 GB | Fits | ~84 tok/s | Q6_K |
| Qwen 3 8B | 6.6 GB | Fits | ~86 tok/s | Q6_K |
| Qwen 3.5 9B | 6.4 GB | Fits | ~86 tok/s | Q6_K |
| Llama 3.1 8B | 6.3 GB | Fits | ~89 tok/s | Q6_K |
| DeepSeek R1 Distill Llama 8B | 6.3 GB | Fits | ~89 tok/s | Q6_K |
| Mistral 7B v0.3 | 5.7 GB | Fits | ~97 tok/s | Q8_0 |
| Gemma 4 E4B | 5.7 GB | Fits | ~96 tok/s | Q8_0 |
| Qwen 2.5 7B | 5.6 GB | Fits | ~99 tok/s | Q8_0 |
| DeepSeek R1 Distill Qwen 7B | 5.6 GB | Fits | ~99 tok/s | Q8_0 |
| Qwen 3 4B | 4.2 GB | Fits | ~153 tok/s | Q8_0 |
| Phi-4 Mini | 4.1 GB | Fits | ~163 tok/s | FP16 / BF16 |
| Gemma 4 E2B | 4.0 GB | Fits | ~150 tok/s | Q8_0 |
| Gemma 3 4B | 3.7 GB | Fits | ~166 tok/s | FP16 / BF16 |
| Qwen 3.5 4B | 3.7 GB | Fits | ~171 tok/s | FP16 / BF16 |
| Ministral 3 3B | 3.5 GB | Fits | ~187 tok/s | FP16 / BF16 |
| Llama 3.2 3B | 3.5 GB | Fits | ~193 tok/s | FP16 / BF16 |
| Llama 3.2 1B | 1.7 GB | Fits | ~512 tok/s | FP16 / BF16 |
| Gemma 3 1B | 1.6 GB | Fits | ~647 tok/s | FP16 / BF16 |
| Ministral 3 14B | 9.7 GB | Tight fit | ~55 tok/s | IQ4_XS |
| Mixtral 8x7B | 28.0 GB | 34% on GPU | ~7.1 tok/s | – |
| Qwen 2.5 32B | 21.4 GB | 44% on GPU | ~3.3 tok/s | – |
| Qwen 2.5 Coder 32B | 21.4 GB | 44% on GPU | ~3.3 tok/s | – |
| DeepSeek R1 Distill Qwen 32B | 21.4 GB | 44% on GPU | ~3.3 tok/s | – |
| Qwen 3 32B | 21.4 GB | 44% on GPU | ~3.3 tok/s | – |
| Qwen 3.5 35B-A3B | 21.0 GB | 45% on GPU | ~32 tok/s | – |
| Qwen 3.6 35B-A3B | 21.0 GB | 45% on GPU | ~32 tok/s | – |
| Gemma 4 31B | 19.8 GB | 47% on GPU | ~3.7 tok/s | – |
| Qwen 3 30B-A3B | 18.8 GB | 50% on GPU | ~28 tok/s | – |
| Qwen3-Coder 30B-A3B | 18.8 GB | 50% on GPU | ~28 tok/s | – |
| Gemma 3 27B | 17.6 GB | 53% on GPU | ~4.7 tok/s | – |
| Qwen 3.5 27B | 16.9 GB | 56% on GPU | ~5.1 tok/s | – |
| Qwen 3.6 27B | 16.9 GB | 56% on GPU | ~5.1 tok/s | – |
| Qwen 3.8 27B | 16.9 GB | 56% on GPU | ~5.1 tok/s | – |
| Mistral Small 3.1 24B | 15.6 GB | 60% on GPU | ~6.1 tok/s | – |
| Gemma 4 26B-A4B | 15.6 GB | 60% on GPU | ~32 tok/s | – |
| gpt-oss-20b | 12.9 GB | 73% on GPU | ~49 tok/s | Q2_K |
| Qwen 2.5 14B | 10.7 GB | 88% on GPU | ~22 tok/s | Q3_K_M |
| DeepSeek R1 Distill Qwen 14B | 10.7 GB | 88% on GPU | ~22 tok/s | Q3_K_M |
| Phi-4 14B | 10.6 GB | 88% on GPU | ~22 tok/s | Q3_K_M |
| Qwen 3 14B | 10.5 GB | 90% on GPU | ~24 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 10GB for local AI
High bandwidth makes it fast, but 10 GB is an awkward size: too small for 14B models with useful context, and only slightly roomier than 8 GB cards.
Among the 2 devices we track with about 10 GB of usable memory, the RTX 3080 10GB is the fastest at generating text, because generation speed follows memory bandwidth. Others in the same class: Intel Arc B570 10GB. They all hold the same models; the faster ones simply answer sooner.
Our picks for the RTX 3080 10GB
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 3.5 9B | Q6_K | 104K | ~86 tok/s |
| Coding | Qwen 3.5 9B | Q6_K | 104K | ~86 tok/s |
| Fastest replies | Qwen 3.5 4B | FP16 / BF16 | 190K | ~171 tok/s |
| Long documents (64K+) | Qwen 3.5 9B | Q6_K | 104K | ~86 tok/s |
| Images in, text out | Gemma 4 E4B | Q8_0 | 128K | ~96 tok/s |
| Image generation | FLUX.1 [dev] | GGUF Q5_K_S | – | – |
| Spec | Value |
|---|---|
| Memory | 10 GB |
| Memory bandwidth | 760 GB/s |
| Architecture | Ampere |
| Released | 2020-09 |
| Llama 3.1 8B Q4_K_M speed | ~89 tok/s |
| Largest model that fits | Ministral 3 14B |
Image and video models on the RTX 3080 10GB
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 | 78% on GPU | 7.3 GB | Fits |
| FLUX.1 [schnell] | 12.1 GB | 78% on GPU | 7.3 GB | Fits |
| Qwen-Image | 20.4 GB | 46% on GPU | 12.3 GB | 77% on GPU |
| Wan 2.2 A14B (T2V / I2V) | 18.8 GB | 50% on GPU | 13.2 GB | 71% on GPU |
| Wan 2.2 TI2V 5B | 8.0 GB | Fits | 6.5 GB | Fits |
| HunyuanVideo | 18.3 GB | 51% on GPU | 13.1 GB | 72% on GPU |
| FLUX.1 Kontext [dev] | 12.3 GB | 77% on GPU | 7.5 GB | Fits |
| FLUX.2 [dev] | 31.0 GB | 30% on GPU | 23.6 GB | 40% on GPU |
| Z-Image Turbo | 6.8 GB | Fits | 4.9 GB | Fits |
| Qwen-Image-Edit 2509 | 20.5 GB | 46% on GPU | 12.4 GB | 76% on GPU |
| LTX-2 | 19.2 GB | 49% on GPU | 12.6 GB | 75% on GPU |
Upgrade path
The next step up is the RTX 2080 Ti 11GB with 11 GB.
RTX 3080 10GB for LLMs: common questions
Can the RTX 3080 10GB run Llama 3.3 70B?
No. It needs about 43.2 GB at Q4_K_M, far more than the 10.0 GB available.
Can the RTX 3080 10GB run Qwen 3 32B?
Only partly. It needs about 21.4 GB at Q4_K_M, so about 44% fits in VRAM and the rest runs from system RAM, which is slow.
Can the RTX 3080 10GB run Qwen 3 14B?
Only partly. It needs about 10.5 GB at Q4_K_M, so about 90% fits in VRAM and the rest runs from system RAM, which is slow. Q3_K_M fits fully.
How fast is the RTX 3080 10GB for LLMs?
About 89 tokens per second for an 8B model at Q4_K_M, based on its 760 GB/s memory bandwidth. Larger models scale down roughly in proportion to their size.