RTX 4080 vs RTX 4090 for local LLMs
For local LLMs the RTX 4090 is the stronger pick: it runs 39 of the top 60 vs 32, and it has the higher speed ceiling. It launched at $400 more.
- The RTX 4090 runs more of the 60 most-downloaded models fully in memory at 4-bit or better: 39 vs 32, because it has more usable memory (about 23 GB vs 15 GB).
- At near-lossless 8-bit or better, the RTX 4090 runs 32 of them vs 30.
- At the same quant, the RTX 4090 has a 1.4× higher speed ceiling (memory bandwidth 1008 vs 717 GB/s). The speed table below shows each card's best quant that fits, so a card with more memory can show a slower, higher-quality setting.
- The RTX 4080 launched at $1,199 vs $1,599 for the RTX 4090 (launch MSRP; street prices differ).
Specs that matter for LLMs
| RTX 4080 | RTX 4090 | |
|---|---|---|
| Memory (VRAM) | 16 GB | 24 GB |
| Usable for a model (our estimate) | 15.2 GB | 22.8 GB |
| Memory bandwidth | 717 GB/s | 1008 GB/s |
| Launch MSRP | $1,199 | $1,599 |
| Launch $ per GB of memory | $75 | $67 |
| Top 60 models that fit (4-bit or better, 8K ctx) | 32 | 39 |
| …of those at 8-bit or better | 30 | 32 |
| Largest top-60 model that fits | gpt-oss 20B | Qwen3 Coder 30B A3B Instruct |
| Offload headroom: more top-60 models via llama.cpp CPU offload (≥3 tok/s est., up to 128 GB RAM) | 18 more (1 more below 3 tok/s) | 7 more (1 more below 3 tok/s) |
Top 60 = the 60 most-downloaded open models we track. Launch MSRP from vendor announcements. How we calculate.
Estimated speed on popular models
Best quant that fits at 8K context, with a tokens/sec ceiling from memory bandwidth (real speed is typically 50–80% of it). "Offload" means part of the model sits in system RAM. Estimates, not benchmarks.
Models only one of them runs
Only the RTX 4080
None.
Only the RTX 4090
- Qwen3.8 27B (28B, 17.6 GB at 4-bit)
- Gemma 4 26B A4B IT (26B, 17.3 GB at 4-bit)
- Qwen3.6 27B (28B, 18.1 GB at 4-bit)
- Qwen3 Coder 30B A3B Instruct (31B, 18.8 GB at 4-bit)
- Qwen3.5 27B (28B, 18.1 GB at 4-bit)
- GLM 4.7 Flash (31B, 18.3 GB at 4-bit)
- DiffusionGemma 26B A4B IT (26B, 17.1 GB at 4-bit)
More comparisons
RTX 3090 vs RTX 4090RTX 4090 vs RTX 5090RTX 4090 vs RX 7900 XTXMac M4 Pro 48GB vs RTX 4090 All GPU comparisons
See every model on the RTX 4080 or the RTX 4090, or try your own settings in the VRAM calculator.