What LLMs Can the RTX 5060 Ti 8GB Run?
The RTX 5060 Ti 8GB has 8 GB of VRAM and 448 GB/s of bandwidth. It runs 18 of 58 models fully at Q4_K_M with 8K context, up to Qwen 3.5 9B, and generates about 53 tokens/s on an 8B model.
18 of 58 models fit
RTX 5060 Ti 8GB (8.0 GB) at Q4_K_M with 8K context. Largest that fits fully: Qwen 3.5 9B.
| Model | Needs | Status | Speed | Best quant that fits |
|---|---|---|---|---|
| Ministral 3 8B | 6.7 GB | Fits | ~50 tok/s | Q5_K_M |
| Qwen 3 8B | 6.6 GB | Fits | ~51 tok/s | Q5_K_M |
| Qwen 3.5 9B | 6.4 GB | Fits | ~51 tok/s | Q5_K_M |
| Llama 3.1 8B | 6.3 GB | Fits | ~53 tok/s | Q5_K_M |
| DeepSeek R1 Distill Llama 8B | 6.3 GB | Fits | ~53 tok/s | Q5_K_M |
| Mistral 7B v0.3 | 5.7 GB | Fits | ~58 tok/s | Q6_K |
| Gemma 4 E4B | 5.7 GB | Fits | ~58 tok/s | Q6_K |
| Qwen 2.5 7B | 5.6 GB | Fits | ~59 tok/s | Q6_K |
| DeepSeek R1 Distill Qwen 7B | 5.6 GB | Fits | ~59 tok/s | Q6_K |
| Qwen 3 4B | 4.2 GB | Fits | ~93 tok/s | Q8_0 |
| Phi-4 Mini | 4.1 GB | Fits | ~98 tok/s | Q8_0 |
| Gemma 4 E2B | 4.0 GB | Fits | ~90 tok/s | Q8_0 |
| Gemma 3 4B | 3.7 GB | Fits | ~100 tok/s | Q8_0 |
| Qwen 3.5 4B | 3.7 GB | Fits | ~103 tok/s | Q8_0 |
| Ministral 3 3B | 3.5 GB | Fits | ~112 tok/s | Q8_0 |
| Llama 3.2 3B | 3.5 GB | Fits | ~117 tok/s | Q8_0 |
| Llama 3.2 1B | 1.7 GB | Fits | ~312 tok/s | FP16 / BF16 |
| Gemma 3 1B | 1.6 GB | Fits | ~410 tok/s | FP16 / BF16 |
| Qwen 2.5 32B | 21.4 GB | 35% on GPU | ~2.9 tok/s | – |
| Qwen 2.5 Coder 32B | 21.4 GB | 35% on GPU | ~2.9 tok/s | – |
| DeepSeek R1 Distill Qwen 32B | 21.4 GB | 35% on GPU | ~2.9 tok/s | – |
| Qwen 3 32B | 21.4 GB | 35% on GPU | ~2.9 tok/s | – |
| Qwen 3.5 35B-A3B | 21.0 GB | 36% on GPU | ~27 tok/s | – |
| Qwen 3.6 35B-A3B | 21.0 GB | 36% on GPU | ~27 tok/s | – |
| Gemma 4 31B | 19.8 GB | 38% on GPU | ~3.1 tok/s | – |
| Qwen 3 30B-A3B | 18.8 GB | 40% on GPU | ~24 tok/s | – |
| Qwen3-Coder 30B-A3B | 18.8 GB | 40% on GPU | ~24 tok/s | – |
| Gemma 3 27B | 17.6 GB | 43% on GPU | ~3.8 tok/s | – |
| Qwen 3.5 27B | 16.9 GB | 45% on GPU | ~4.0 tok/s | – |
| Qwen 3.6 27B | 16.9 GB | 45% on GPU | ~4.0 tok/s | – |
| Qwen 3.8 27B | 16.9 GB | 45% on GPU | ~4.0 tok/s | – |
| Mistral Small 3.1 24B | 15.6 GB | 48% on GPU | ~4.7 tok/s | – |
| Gemma 4 26B-A4B | 15.6 GB | 48% on GPU | ~25 tok/s | – |
| gpt-oss-20b | 12.9 GB | 58% on GPU | ~34 tok/s | – |
| Qwen 2.5 14B | 10.7 GB | 70% on GPU | ~11 tok/s | Q2_K |
| DeepSeek R1 Distill Qwen 14B | 10.7 GB | 70% on GPU | ~11 tok/s | Q2_K |
| Phi-4 14B | 10.6 GB | 71% on GPU | ~11 tok/s | Q2_K |
| Qwen 3 14B | 10.5 GB | 72% on GPU | ~11 tok/s | Q2_K |
| Ministral 3 14B | 9.7 GB | 78% on GPU | ~14 tok/s | Q2_K |
| Mistral Nemo 12B | 9.0 GB | 84% on GPU | ~18 tok/s | Q2_K |
| Gemma 3 12B | 8.8 GB | 86% on GPU | ~20 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 | – | – |
| Mixtral 8x7B | 28.0 GB | Too small | – | – |
RTX 5060 Ti 8GB for local AI
Same chip and bandwidth as the 16 GB 5060 Ti but half the memory. For local AI the 16 GB version is worth the extra money; this one is limited to 8B-class models.
Among the 9 devices we track with about 8 GB of usable memory, the RTX 5060 Ti 8GB ranks 5 of 9 for text-generation speed, because generation speed follows memory bandwidth. Others in the same class: RTX 3070 Ti 8GB, RTX 3060 Ti 8GB, RTX 3070 8GB, RTX 5060 8GB. They all hold the same models; the faster ones simply answer sooner.
Our picks for the RTX 5060 Ti 8GB
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 | Q5_K_M | 44K | ~51 tok/s |
| Coding | Qwen 3.5 9B | Q5_K_M | 44K | ~51 tok/s |
| Fastest replies | Qwen 3.5 4B | Q8_0 | 130K | ~103 tok/s |
| Long documents (64K+) | Gemma 4 E4B | Q6_K | 124K | ~58 tok/s |
| Images in, text out | Gemma 4 E4B | Q6_K | 124K | ~58 tok/s |
| Image generation | FLUX.1 [dev] | GGUF Q4_K_S / NF4 | – | – |
| Spec | Value |
|---|---|
| Memory | 8 GB |
| Memory bandwidth | 448 GB/s |
| Architecture | Blackwell |
| Released | 2025-04 |
| Llama 3.1 8B Q4_K_M speed | ~53 tok/s |
| Largest model that fits | Qwen 3.5 9B |
Image and video models on the RTX 5060 Ti 8GB
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 | 87% on GPU | 6.4 GB | Fits |
| FLUX.1 [dev] | 12.1 GB | 62% on GPU | 7.3 GB | Fits |
| FLUX.1 [schnell] | 12.1 GB | 62% on GPU | 7.3 GB | Fits |
| Qwen-Image | 20.4 GB | 37% on GPU | 12.3 GB | 61% on GPU |
| Wan 2.2 A14B (T2V / I2V) | 18.8 GB | 40% on GPU | 13.2 GB | 57% on GPU |
| Wan 2.2 TI2V 5B | 8.0 GB | Tight fit | 6.5 GB | Fits |
| HunyuanVideo | 18.3 GB | 41% on GPU | 13.1 GB | 57% on GPU |
| FLUX.1 Kontext [dev] | 12.3 GB | 61% on GPU | 7.5 GB | Fits |
| FLUX.2 [dev] | 31.0 GB | Too small | 23.6 GB | 32% on GPU |
| Z-Image Turbo | 6.8 GB | Fits | 4.9 GB | Fits |
| Qwen-Image-Edit 2509 | 20.5 GB | 37% on GPU | 12.4 GB | 61% on GPU |
| LTX-2 | 19.2 GB | 39% on GPU | 12.6 GB | 60% on GPU |
Upgrade path
The next step up is the Intel Arc B570 10GB with 10 GB.
RTX 5060 Ti 8GB for LLMs: common questions
Can the RTX 5060 Ti 8GB run Llama 3.3 70B?
No. It needs about 43.2 GB at Q4_K_M, far more than the 8.0 GB available.
Can the RTX 5060 Ti 8GB run Qwen 3 32B?
Only partly. It needs about 21.4 GB at Q4_K_M, so about 35% fits in VRAM and the rest runs from system RAM, which is slow.
Can the RTX 5060 Ti 8GB run Qwen 3 14B?
Only partly. It needs about 10.5 GB at Q4_K_M, so about 72% fits in VRAM and the rest runs from system RAM, which is slow. Q2_K fits fully.
How fast is the RTX 5060 Ti 8GB for LLMs?
About 53 tokens per second for an 8B model at Q4_K_M, based on its 448 GB/s memory bandwidth. Larger models scale down roughly in proportion to their size.