Hardware / NVIDIA
Can an RTX 4090 run Llama 3.3 70B?
RTX 4090 has 24 GB VRAM. About 21.6 GB is treated as usable. 24 GB GDDR6X. Single-card rows only; multi-GPU rigs are separate entries. The title asks about Llama 3.3 70B because it is the largest catalog model still in range of this memory.
Manufacturer page for RTX 4090
Compatibility
| Model | Q4 | Q8 | FP16 | MXFP4 |
|---|---|---|---|---|
| Qwen3.6 35B-A3B Qwen · 35B stored · 3B active | 38.1 GB Over estimate · KV at 8k No measured run | 70.9 GB Over estimate · KV at 8k No measured run | — | |
| Qwen3.8 27B Qwen · 27B stored | 29.9 GB Over estimate · KV at 8k No measured run | 55.3 GB Over estimate · KV at 8k No measured run | — | |
| Gemma 4 26B-A4B Gemma · 25.2B stored · 3.8B active | 27.5 GB Over estimate No measured run | 51.1 GB Over estimate No measured run | — | |
| Gemma 4 12B Gemma · 12B stored | 13.4 GB Fits estimate No measured run | 24.6 GB Over estimate No measured run | — | |
| Llama 2 7B Llama · 7B stored | 12.2 GB Fits estimate · KV at 8k No measured run | 18.8 GB Fits estimate · KV at 8k No measured run | — | |
| Gemma 4 31B Gemma · 30.7B stored | 19.4 GB Fits estimate No measured run | 33.4 GB Over estimate No measured run | 62.1 GB Over estimate No measured run | — |
| Qwen3 30B-A3B Qwen · 30B stored · 3B active | 18.9 GB Fits estimate No measured run | 32.6 GB Over estimate No measured run | 60.8 GB Over estimate No measured run | — |
| gpt-oss 20B gpt-oss · 20.9B stored · 3.6B active | 13.4 GB Fits estimate No measured run | 23.0 GB Tight estimate No measured run | 42.6 GB Over estimate No measured run | |
| Qwen3 14B Qwen · 14B stored | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Over estimate No measured run | — |
| DeepSeek R1 Distill 14B DeepSeek · 14B stored | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Over estimate No measured run | — |
| Gemma 3 12B Gemma · 12B stored | 8.0 GB Fits estimate No measured run | 13.5 GB Fits estimate No measured run | 24.8 GB Over estimate No measured run | — |
| Llama 3 8B Llama · 8B stored | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run | — |
| Llama 3.1 8B Llama · 8B stored | 6.6 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run | — | |
| Qwen3 8B Qwen · 8B stored | 5.6 GB Fits estimate No measured run | 9.3 GB Fits estimate No measured run | 16.8 GB Fits estimate No measured run | — |
| Gemma 4 E4B Gemma · 8B stored | 5.6 GB Fits estimate No measured run | 9.3 GB Fits estimate No measured run | 16.8 GB Fits estimate No measured run | — |
| DeepSeek R1 Distill 8B DeepSeek · 8B stored | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run | — |
| Llama 3.2 3B Llama · 3B stored | 3.4 GB Fits estimate · KV at 8k No measured run | 4.8 GB Fits estimate · KV at 8k No measured run | 7.6 GB Fits estimate · KV at 8k No measured run | — |
| DeepSeek R1 671B DeepSeek · 671B stored · 37B active | 408 GB Over estimate No measured run | 714 GB Over estimate No measured run | 1343 GB Over estimate No measured run | — |
| Llama 3.1 405B Llama · 405B stored | 250 GB Over estimate · KV at 8k No measured run | 435 GB Over estimate · KV at 8k No measured run | 815 GB Over estimate · KV at 8k No measured run | — |
| Qwen3 235B-A22B Qwen · 235B stored · 22B active | 143 GB Over estimate No measured run | 250 GB Over estimate No measured run | 471 GB Over estimate No measured run | — |
| gpt-oss 120B gpt-oss · 117B stored · 5.1B active | 71.6 GB Over estimate No measured run | 125 GB Over estimate No measured run | 234 GB Over estimate No measured run | 61.5 GB Over checkpoint No measured run |
| Llama 3 70B Llama · 70B stored | 45.7 GB Over estimate · KV at 8k No measured run | 77.6 GB Over estimate · KV at 8k No measured run | 143 GB Over estimate · KV at 8k No measured run | — |
| Llama 3.1 70B Llama · 70B stored | 45.7 GB Over estimate · KV at 8k No measured run | 77.6 GB Over estimate · KV at 8k No measured run | 143 GB Over estimate · KV at 8k No measured run | — |
| Llama 3.3 70B Llama · 70B stored | 45.7 GB Over estimate · KV at 8k No measured run | 77.6 GB Over estimate · KV at 8k No measured run | 143 GB Over estimate · KV at 8k No measured run | — |
| DeepSeek R1 Distill 70B DeepSeek · 70B stored | 45.7 GB Over estimate · KV at 8k No measured run | 77.6 GB Over estimate · KV at 8k No measured run | 143 GB Over estimate · KV at 8k No measured run | — |
Measured runs on this device
- Llama 3.2 3B · not stated · 334.67 tok/s · llama.cpp source
- gpt-oss 20B · not stated · 279.65 tok/s · llama.cpp source
- gpt-oss 20B · MXFP4 (12.1 GB GGUF), reasoning low · 238.6 tok/s · llama.cpp b11669 (CUDA) source
- Llama 3.2 3B · not stated · 237.05 tok/s · llama.cpp source
- gpt-oss 20B · llama-bench tg128 (quant per result) · 203 tok/s · llama.cpp source
- Llama 2 7B · Q4_0 · 188.96 tok/s · llama.cpp CUDA (FA) source
- Gemma 4 26B-A4B · llama-bench tg128 (quant per result) · 164 tok/s · llama.cpp source
- Gemma 4 26B-A4B · UD-IQ4_XS (13.6 GB) · 161.4 tok/s · llama.cpp b11669 (CUDA) source
- Qwen3.6 35B-A3B · Q4_K_M · 160.6 tok/s · llama.cpp b8931 source
- Gemma 4 12B · QAT Q4_0 (7.0 GB, Google's file) · 99.7 tok/s · llama.cpp b11669 (CUDA) source
- Gemma 4 12B · llama-bench tg128 (quant per result) · 98.1 tok/s · llama.cpp source
- Gemma 4 12B · QAT Q4_0 · 97.7 tok/s · llama.cpp b8931 source
- DeepSeek R1 Distill 14B · not stated · 92.49 tok/s · llama.cpp source
- Qwen3.8 27B · Q4_K_M (16.8 GB, LM Studio catalogue) + the model's own MTP (LM Studio default) · 62.4 tok/s · speculative · LM Studio 2.55.0 (llama.cpp CUDA) source
- Llama 3.1 8B · Q8 · 52.99 tok/s · llama.cpp-based source
- Gemma 4 31B · llama-bench tg128 (quant per result) · 43.8 tok/s · llama.cpp source
- Qwen3.8 27B · Q4_K_M · 43.1 tok/s · llama.cpp build 11803 (a37cc4610) source
- Qwen3.8 27B · Q4_K_M · 43.06 tok/s · llama.cpp (df18bee) source
- Qwen3.8 27B · Q4_K_M · 43.0 tok/s · llama.cpp build 11803 (a37cc4610) source
- Qwen3.8 27B · Q4_K_M · 42.63 tok/s · llama.cpp (df18bee) source
- Llama 3.1 70B · not stated · 3.1 tok/s · GPU+CPU offload source