HARDWARE BENCHMARK & VRAM ENVELOPE • CONSUMER GPU16 GB VRAM • 288 GB/s
What Models Can Run on NVIDIA GeForce RTX 4060 Ti (16GB GDDR6)?
16 GB VRAM288 GB/s Bandwidth165W TDPMSRP: $449Used / eBay: ~$380Cloud: $0.2/hr on Vast.ai
NVIDIA GeForce RTX 4060 Ti (16GB GDDR6) provides 16 GB of usable memory with 288 GB/s memory bandwidth at 165W TDP. Lowest-cost 16GB VRAM GPU for running 8B–14B models and LoRA fine-tuning on a budget.
✕ OOM25.22 GB (158%)0 t/s
Qwen 2.5 Coder 32B Instruct on NVIDIA GeForce RTX 4060 Ti (16GB GDDR6)
✕ Out of Memory — Exceeds VRAM Capacity
✕ OOM
Required VRAM
25.22 GB
158% of hardware capacity (16 GB)Est. Decode Speed
0 tok/s
Dense model @ 288 GB/sAvailable Headroom
-9.22 GB
Needs +9.22 GB more VRAMMemory Allocation & Headroom
25.22 GB allocated of 16 GB capacity
158% utilized
Weights: 19.5 GB
KV: (32K): 4.29 GB
Overhead: 1.43 GB
Deficit: -9.22 GB
Architecture & Throughput Transparency: Single-user decode speed (~0 tok/s) is memory-bandwidth bound at batch size = 1 on NVIDIA GeForce RTX 4060 Ti (16GB GDDR6) (288 GB/s). Prompt prefill / TTFT (~0 tok/s) is compute-bound and utilizes GPU Tensor cores. Actual latency varies with FlashAttention-2 and runtime engine (Ollama/vLLM/llama.cpp).
Out of VRAM? Don't downgrade model quality.
Out of VRAMSpin up an on-demand cloud GPU instance in 60 seconds with pre-installed Ollama and vLLM. (Qwen 2.5 Coder 32B Instruct @ 25.22 GB VRAM)
RunPod Cloud GPUsBest 1-Click Ollama & vLLM
$0.38/hr (RTX 4090 Spot) – $2.39/hr (H100)Vast.ai GPU MarketplaceCheapest Dual RTX 3090 / 4090
$0.18/hr (RTX 3060) – $0.78/hr (2x RTX 3090)Lambda GPU CloudEnterprise 8x H100 Clusters
$2.49/hr (H100) – $19.92/hr (8x H100)Quantization Precision Matrix
32K ctx • KV: Q8_0| Quantization | Weights | KV Cache | Total VRAM | Est. Speed | Fit Status |
|---|---|---|---|---|---|
| FP1616 bpw | 65 GB | 4.29 GB | 72.32 GB (452%) | 0 t/s | OOM |
| Q8_08.5 bpw | 34.45 GB | 4.29 GB | 40.7 GB (254%) | 0 t/s | OOM |
| Q6_K6.56 bpw | 26.65 GB | 4.29 GB | 32.62 GB (204%) | 0 t/s | OOM |
| Q5_K_M5.68 bpw | 23.07 GB | 4.29 GB | 28.92 GB (181%) | 0 t/s | OOM |
| Q4_K_M4.8 bpw | 19.5 GB | 4.29 GB | 25.22 GB (158%) | 0 t/s | OOM |
| FP44.25 bpw | 17.23 GB | 4.29 GB | 22.87 GB (143%) | 0 t/s | OOM |
| IQ3_XS3.3 bpw | 13.32 GB | 4.29 GB | 18.83 GB (118%) | ~3 t/s | PARTIAL |
All Open-Weights Models Tested on NVIDIA GeForce RTX 4060 Ti (16GB GDDR6) (Q4_K_M @ 32K Context)
Standard Q4_K_M precision with 32K context window and Q8_0 KV cache
| Model | Architecture | Total VRAM Needed | Headroom | Est. Decode Speed | Compatibility | Detailed Config |
|---|---|---|---|---|---|---|
| Qwen 2.5 Coder 32B Instruct Alibaba Cloud | 32.5B Dense | 25.22 GB(158%) | -9.22 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| DeepSeek-R1 (671B MoE) DeepSeek | 671B MoE | 427.26 GB(999%) | -411.26 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| DeepSeek-V3 (671B MoE) DeepSeek | 671B MoE | 427.26 GB(999%) | -411.26 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Meta Llama 3.3 70B Instruct Meta AI | 70.6B Dense | 49.96 GB(312%) | -33.96 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| DeepSeek-R1 Distill Qwen 32B DeepSeek | 32.8B Dense | 25.41 GB(159%) | -9.41 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| DeepSeek-R1 Distill Qwen 14B DeepSeek | 14.8B Dense | 13.16 GB(82%) | +2.84 GB | ~19 tok/s | ✓ FITS | Configure CLI → |
| Qwen 2.5 72B Instruct Alibaba Cloud | 72.7B Dense | 51.27 GB(320%) | -35.27 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Meta Llama 3.1 8B Instruct Meta AI | 8B Dense | 7.87 GB(49%) | +8.13 GB | ~35 tok/s | ✓ FITS | Configure CLI → |
| Microsoft Phi-4 14B Microsoft | 14.7B Dense | 13.24 GB(83%) | +2.76 GB | ~19 tok/s | ✓ FITS | Configure CLI → |
| DeepSeek Coder V2 236B MoE DeepSeek | 236B MoE | 147.91 GB(924%) | -131.91 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Mistral Large 2 (123B Instruct) Mistral AI | 123B Dense | 83.04 GB(519%) | -67.04 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Meta Llama 3.1 405B Instruct Meta AI | 405B Dense | 260.72 GB(999%) | -244.72 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Google Gemma 2 27B Instruct Google | 27.2B Dense | 19.18 GB(120%) | -3.18 GB | ~2 tok/s | ! PARTIAL | Configure CLI → |
| Google Gemma 2 9B Instruct Google | 9.2B Dense | 7.87 GB(49%) | +8.13 GB | ~32 tok/s | ✓ FITS | Configure CLI → |
| Qwen 3.8 27B Instruct Alibaba Cloud | 27.2B Dense | 21.93 GB(137%) | -5.93 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Qwen 3.8 235B-A22B MoE Alibaba Cloud | 235B MoE | 149.84 GB(937%) | -133.84 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Qwen 3.6 35B-A3B MoE Alibaba Cloud | 35B MoE | 24.1 GB(151%) | -8.1 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| DeepSeek-V4.1-Flash (552B Engram MoE) DeepSeek | 552B MoE | 343.85 GB(999%) | -327.85 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Meta Muse Spark Open (816B-A42B MoE) Meta AI | 816B MoE | 512.86 GB(999%) | -496.86 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Google Gemma 4 26B MoE Google | 26.4B MoE | 20.23 GB(126%) | -4.23 GB | ~13 tok/s | ! PARTIAL | Configure CLI → |
| Google Gemma 4 E4B (Edge 4B) Google | 4.1B Dense | 4.24 GB(27%) | +11.76 GB | ~69 tok/s | ✓ FITS | Configure CLI → |
| Meta Llama 4 Scout (109B-A17B MoE) Meta AI | 109B MoE | 71.66 GB(448%) | -55.66 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| Microsoft Phi-4 Mini 3.8B Microsoft | 3.8B Dense | 3.92 GB(25%) | +12.08 GB | ~75 tok/s | ✓ FITS | Configure CLI → |
| Mistral Small 3 24B Instruct Mistral AI | 24B Dense | 18.33 GB(115%) | -2.33 GB | ~3 tok/s | ! PARTIAL | Configure CLI → |
| DeepSeek-R1 Distill Llama 70B DeepSeek | 70.6B Dense | 49.96 GB(312%) | -33.96 GB | 0 (OOM) | ✕ OOM | Configure CLI → |
| DeepSeek-R1 Distill Qwen 7B DeepSeek | 7.6B Dense | 6.41 GB(40%) | +9.59 GB | ~39 tok/s | ✓ FITS | Configure CLI → |
| Qwen 2.5 Coder 7B Instruct Alibaba Cloud | 7.6B Dense | 6.41 GB(40%) | +9.59 GB | ~39 tok/s | ✓ FITS | Configure CLI → |