NVIDIA GeForce RTX 4080
16 GB decides what fits. 716.8 GB/s decides how fast it runs once it does.
Open in the calculator →Best models for 16 GB, on every card that size →
Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
- Largest popular model that fitsgpt-oss-20b21B params · Q4_K_M · needs 13.8 GB~195 tok/s Faster than you readOpen in the calculator →
- Best fast pickERNIE-4.5-21B-A3B-PT22B params · Q4_K_M · needs 14.7 GB~192 tok/s Faster than you readOpen in the calculator →
- Most downloaded that fitsQwen3.5-9B9.7B params · Q4_K_M · needs 7.05 GB~100 tok/s Faster than you readOpen in the calculator →
At 8,192 tokens of context with the whole model in device memory. Speeds are estimates from memory bandwidth, not benchmarks run on this card.
153 of 320 fit entirely
153 of the 320 models the engine can size fit entirely in device memory at Q4_K_M where it is published, otherwise the nearest published format, and 8,192 tokens. 73 run with some layers on system memory (32 GB assumed), and 94 do not run at all.
Featured models · Q4_K_M at 8,192 tokens, including offload
| Model | Needs | Verdict | Decode | Calculator |
|---|---|---|---|---|
| Qwen3.5-2B2.3B parameters | 2.32 GB | fits | ~395 tok/s | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters | 3.46 GB | fits | ~183 tok/s | Open → |
| Qwen3-VL-8B-Instruct8.8B parameters | 7.04 GB | fits | ~83 tok/s | Open → |
| Qwen3.5-9B9.7B parameters | 7.05 GB | fits | ~100 tok/s | Open → |
| gemma-4-12B-it12B parameters | 9.54 GB | fits | ~60 tok/s | Open → |
| gpt-oss-20b21B parameters | 13.8 GB | fits | ~195 tok/s | Open → |
| Qwen3.8-27B28B parameters | 18.6 GB | 10 of 64 layers on system RAM (2.66 GB) | ~16 tok/s with offload | Open → |
| Qwen3.6-27B28B parameters | 18.6 GB | 10 of 64 layers on system RAM (2.66 GB) | ~16 tok/s with offload | Open → |
| Kimi-Linear-48B-A3B-Instruct49B parameters | 30.4 GB | 14 of 27 layers on system RAM (15.3 GB) | ~58 tok/s with offload | Open → |
| Qwen3.8-Flash-Next180B parameters | 111.6 GB | needs 96.7 GB of system RAM; 32 GB assumed | does not run | Open → |
| DeepSeek-V4-Flash-Vision-Exp305B parameters | 188.1 GB | needs 174.2 GB of system RAM; 32 GB assumed | does not run | Open → |
| GLM-5.3-Flash321B parameters | 198.3 GB | needs 184.1 GB of system RAM; 32 GB assumed | does not run | Open → |
These examples are selected from prominent labs using the catalogue’s latest Hugging Face 30-day downloads and repository-creation freshness signal, with newer releases guaranteed a place. Offloaded rows assume 32 GB of system RAM, and a speed is only shown for a row that runs. Fitting in memory is not the same as loading: whether the runtime and version you have supports each architecture and format on this machine has not been tested here. Each “Open” link carries the same model, format, context and RAM into the calculator.
Fits entirely in NVIDIA GeForce RTX 4080 memory — 153 of 320 sized models
The most demanding model that fits is gpt-neox-20b at Q4_K_M: 15.7 GB of the 16 GB, leaving 0.25 GB spare.
Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 716.8 GB/s. Each row is a run of the engine for this configuration; the rows start with current, prominent releases and “fits” is memory, not a tested runtime. Older or less prominent models remain available through this search and “Show all”.
Showing 40 of 153 models that fit.
| Model | Format | Needs | Spare | Decode | Downloads / 30d | Calculator |
|---|---|---|---|---|---|---|
| Qwen3.5-9BQwen · 9.7B params | Q4_K_M | 7.05 GB | 8.95 GB | ~100 tok/s | 9M | Open → |
| Qwen3.5-4BQwen · 4.7B params | Q4_K_M | 3.98 GB | 12.0 GB | ~180 tok/s | 7.8M | Open → |
| gemma-4-12B-itGoogle · 12B params | Q4_K_M | 9.54 GB | 6.46 GB | ~60 tok/s | 1.9M | Open → |
| Qwen3.5-2BQwen · 2.3B params | Q4_K_M | 2.32 GB | 13.7 GB | ~395 tok/s | 4.9M | Open → |
| gemma-4-E4B-itGoogle · 8.0B params | Q4_K_M | 5.86 GB | 10.1 GB | ~161 tok/s | 4.4M | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params | Q4_K_M | 3.46 GB | 12.5 GB | ~183 tok/s | 3.4M | Open → |
| gemma-4-E2B-itGoogle · 5.1B params | Q4_K_M | 4.02 GB | 12.0 GB | ~426 tok/s | 3M | Open → |
| Qwen3.5-0.8BQwen · 873M params | Q4_K_M | 1.46 GB | 14.5 GB | ~866 tok/s | 2.6M | Open → |
| Qwen3-VL-8B-InstructQwen · 8.8B params | Q4_K_M | 7.04 GB | 8.96 GB | ~83 tok/s | 14.6M | Open → |
| North-Micro-Vision-InstructCohereLabs · 2.5B params | Q4_K_M | 2.99 GB | 13.0 GB | ~260 tok/s | 180.7K | Open → |
| granite-4.2-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 8.51 GB | ~75 tok/s | 128.4K | Open → |
| granite-4.1-3bIBM · 3.4B params | Q4_K_M | 3.72 GB | 12.3 GB | ~176 tok/s | 521.8K | Open → |
| LFM2.5-2.6BLiquidAI · 2.7B params | Q4_K_M | 2.61 GB | 13.4 GB | ~282 tok/s | 108.1K | Open → |
| Qwen3-VL-4B-InstructQwen · 4.4B params | Q4_K_M | 4.72 GB | 11.3 GB | ~132 tok/s | 3.5M | Open → |
| Qwen3-VL-2B-InstructQwen · 2.1B params | Q4_K_M | 3.05 GB | 13.0 GB | ~239 tok/s | 2.8M | Open → |
| granite-4.2-3bIBM · 3.7B params | Q4_K_M | 3.72 GB | 12.3 GB | ~176 tok/s | 50.6K | Open → |
| LFM2.5-230MLiquidAI · 230M params | Q4_K_M | 1.05 GB | 14.9 GB | ~1967 tok/s | 88.6K | Open → |
| Qwen3-0.6BQwen · 752M params | Q4_K_M | 2.22 GB | 13.8 GB | ~366 tok/s | 29.7M | Open → |
| gpt-oss-20bOpenAI · 21B params | Q4_K_M | 13.8 GB | 2.24 GB | ~195 tok/s | 6.6M | Open → |
| granite-4.1-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 8.51 GB | ~75 tok/s | 179.3K | Open → |
| LFM2.5-VL-3BLiquidAI · 3.1B params | Q4_K_M | 2.85 GB | 13.1 GB | ~282 tok/s | 26.7K | Open → |
| MiMo-V2.6-Distill-Qwen-9BNEWXiaomiMiMo · 9.4B params | Q4_K_M | 6.90 GB | 9.10 GB | ~100 tok/s | 14.6K | Open → |
| Qwen3-4B-Instruct-2507Qwen · 4.0B params | Q4_K_M | 4.72 GB | 11.3 GB | ~132 tok/s | 3.7M | Open → |
| Ling-3.0-tinyinclusionAI · 7.9B params | Q4_K_M | 5.85 GB | 10.1 GB | ~568 tok/s | 17.7K | Open → |
| Qwen3-8BQwen · 8.2B params | Q4_K_M | 7.04 GB | 8.96 GB | ~83 tok/s | 10.7M | Open → |
| Olmo-3-7B-Instructallenai · 7.3B params | Q4_K_M | 7.96 GB | 8.04 GB | ~70 tok/s | 481.7K | Open → |
| Qwen3-4BQwen · 4.0B params | Q4_K_M | 4.51 GB | 11.5 GB | ~132 tok/s | 7.8M | Open → |
| LFM2.5-8B-A1BLiquidAI · 8.5B params | Q4_K_M | 6.06 GB | 9.94 GB | ~440 tok/s | 32.4K | Open → |
| LFM2.5-350MLiquidAI · 354M params | Q4_K_M | 1.13 GB | 14.9 GB | ~1270 tok/s | 69.9K | Open → |
| Hy-MT2-1.8BTencent · 2.0B params | Q4_K_M | 2.47 GB | 13.5 GB | ~292 tok/s | 28.9K | Open → |
| LLaDA2.0-miniinclusionAI · 16B params | Q4_K_M | 11.0 GB | 5.00 GB | ~455 tok/s | 217.2K | Open → |
| LFM2.5-1.2B-InstructLiquidAI · 1.2B params | Q4_K_M | 1.63 GB | 14.4 GB | ~469 tok/s | 119.2K | Open → |
| Ministral-3-14B-Instruct-2512Mistral AI · 14B params | Q4_K_M | 10.4 GB | 5.62 GB | ~53 tok/s | 251K | Open → |
| Qwen3-1.7BQwen · 2.0B params | Q4_K_M | 3.02 GB | 13.0 GB | ~239 tok/s | 3.1M | Open → |
| Nemotron-3.5-Content-SafetyNVIDIA · 4.3B params | Q4_K_M | 3.73 GB | 12.3 GB | ~176 tok/s | 14.1K | Open → |
| Hy-MT2-7BTencent · 8.0B params | Q4_K_M | 6.50 GB | 9.50 GB | ~86 tok/s | 15.4K | Open → |
| Qwen3-14BQwen · 15B params | Q4_K_M | 11.1 GB | 4.86 GB | ~49 tok/s | 2.7M | Open → |
| GLM-4.6V-Flashzai-org · 10B params | Q4_K_M | 7.45 GB | 8.55 GB | ~85 tok/s | 103.7K | Open → |
| Qwen2.5-VL-7B-InstructQwen · 8.3B params | Q4_K_M | 6.36 GB | 9.64 GB | ~101 tok/s | 5.8M | Open → |
| SmolLM3-3BHuggingFaceTB · 3.1B params | Q4_K_M | 3.46 GB | 12.5 GB | ~194 tok/s | 617K | Open → |
Sized at the format most people actually download, not at FP16. The catalogue ordered by downloads →
Rent an RTX 4080 by the hour
What the NVIDIA GeForce RTX 4080 costs on Vast.ai and RunPod right now, per machine, from one card to eight. Every price is read from the provider's own API.
Buy one or rent one?
Your price, your hours, your electricity. Everything else is arithmetic.
Watts start at the NVIDIA GeForce RTX 4080’s published board power (320 W), an upper bound: decoding rarely holds a card at its limit. Rent starts at the cheapest live price (Vast.ai). The electricity price is a placeholder — put yours in.
At 4 h a day, renting costs $394.20 a year.
- That is $32.85 a month, and nothing when the machine is stopped.
- Owning would cost $116.80 a year in electricity, on top of the price.
- Every $1,000 of purchase price takes 3.6 years of this use to earn back.
Enter the price you would pay to see the exact break-even.
On-demand prices for the whole machine. Vast hosts below 98% measured reliability are left out; RunPod’s Community Cloud is vetted third-party hosts and its Secure Cloud is data-centre capacity. Every rentable card compared.
Referral links Vast.ai, RunPod and Novita pay us a share of what you spend if you sign up through these buttons. It costs you nothing, and it never decides an order or a recommendation: both are computed from the live price and the speed, and options that pay us nothing are listed and recommended on the same terms. How we rank
Find the NVIDIA GeForce RTX 4080: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
The RTX 4080, model by model
One page per model: whether it fits this device, at which formats, and how fast.
The specification behind every figure
What the manufacturer publishes for this device, and the pages it was read from.
Manufacturer specification
| Memory scope | dedicated |
|---|---|
| Capacity | 16 GB |
| Published options | 16 GB |
| Bandwidth | 716.8 GB/s |
| Memory type | GDDR6X |
| Bus width | 256-bit |
| FP32 peak | 48.7 TFLOPS |
| Dense matrix peak | 97.5 TFLOPS (FP16 Tensor with FP32 accumulate, dense) |
| Total Graphics Power (TGP) | 320 W |
Source ledger
Published capacity is a hardware ceiling, not guaranteed free runtime memory. The calculator shows the runtime reserve separately rather than folding it into a single number.
Run the diagnostic on the NVIDIA GeForce RTX 4080 →