What can an RTX 3090 24GB run?
The RTX 3090 24GB has 24 GB of VRAM. The table below checks every language model in our calculator at three quantizations with an 8K-token context, using the same file sizes and fit rule as the rest of the site.
Best model for the RTX 3090 24GB: Gemma 4 31B. It is the largest model in our calculator (31.3B parameters) that fits comfortably at 4-bit: Q4_K_M plus an 8K-token FP16 KV cache needs 19.6 GB, under 90% of 24 GB. The highest precision it fits comfortably at is 4-bit (Q4_K_M). In total, 15 of the 30 language models we track fit comfortably at 4-bit on this card.
| Model | 4-bit (Q4_K_M) | 8-bit (Q8_0) | 16-bit (FP16/BF16) |
|---|---|---|---|
| Gemma 4 31B*Google | 19.6 GB · Fits | 32.6 GB · Too big | 61.4 GB · Too big |
| Qwen3.8 27BAlibaba Qwen | 18.0 GB · Fits | 29.7 GB · Too big | 55.2 GB · Too big |
| Gemma 4 26B A4B*Google | 17.0 GB · Fits | 26.9 GB · Too big | 50.5 GB · Too big |
| LFM2.5-24B-A2BLiquid AI | 14.7 GB · Fits | 25.7 GB · Too big | 48.1 GB · Too big |
| gpt-oss-20bOpenAI | 11.9 GB · Fits | 12.3 GB · Fits | 14.0 GB · Fits |
| Qwen2.5 14B InstructAlibaba Qwen | 10.6 GB · Fits | 17.3 GB · Fits | 31.2 GB · Too big |
| Qwen3 14BAlibaba Qwen | 10.3 GB · Fits | 17.0 GB · Fits | 30.9 GB · Too big |
| DeepSeek-R1-0528-Qwen3-8BDeepSeek | 6.2 GB · Fits | 9.9 GB · Fits | 17.6 GB · Fits |
| Llama 3.1 8B InstructMeta | 6.0 GB · Fits | 9.6 GB · Fits | 17.1 GB · Fits |
| Nemotron 3.5 Bolt E4B*NVIDIA | 6.2 GB · Fits | 8.2 GB · Fits | 15.1 GB · Fits |
| Qwen2.5 7B InstructAlibaba Qwen | 5.2 GB · Fits | 8.6 GB · Fits | 15.7 GB · Fits |
| Mistral 7B Instruct v0.3Mistral AI | 5.4 GB · Fits | 8.8 GB · Fits | 15.6 GB · Fits |
| Spark-X2.6 4BXHToken | 3.8 GB · Fits | 4.7 GB · Fits | 8.5 GB · Fits |
| Llama 3.2 3B InstructMeta | 3.0 GB · Fits | 4.4 GB · Fits | 7.4 GB · Fits |
| LFM3 1.7BLiquid AI | 1.2 GB · Fits | 1.9 GB · Fits | 3.6 GB · Fits |
| Qwen3.6 35B-A3BAlibaba Qwen | 22.5 GB · Tight | 38.0 GB · Too big | 71.2 GB · Too big |
| Qwen3.8-35B-A3B (Empero Distill)Empero | 21.9 GB · Tight | 38.0 GB · Too big | 71.2 GB · Too big |
| Nanbeige4.3 33BNanbeige | 22.5 GB · Tight | 36.9 GB · Too big | 68.0 GB · Too big |
| Qwen2.5 32B InstructAlibaba Qwen | 22.0 GB · Tight | 37.0 GB · Too big | 67.7 GB · Too big |
| Qwen3 32BAlibaba Qwen | 21.9 GB · Tight | 37.0 GB · Too big | 67.7 GB · Too big |
| Kimi K3Moonshot AI | 1,508.9 GB · Too big | 1,561.4 GB · Too big | n/a |
| Mistral Large 4 (Le Chonk)Mistral AI | 635.5 GB · Too big | 1,115.8 GB · Too big | 2,099.5 GB · Too big |
| DeepSeek-V4.1-Flash-1017DeepSeek | 500.7 GB · Too big | 508.4 GB · Too big | n/a |
| Qwen3.8 Flash NextAlibaba Qwen | 119.8 GB · Too big | 188.5 GB · Too big | 354.2 GB · Too big |
| Ornith-1.5-122BOrnith | 79.9 GB · Too big | 132.8 GB · Too big | 249.6 GB · Too big |
| gpt-oss-120bOpenAI | 63.1 GB · Too big | 63.7 GB · Too big | 65.7 GB · Too big |
| Llama 3.1 70B InstructMeta | 45.2 GB · Too big | 77.7 GB · Too big | 143.8 GB · Too big |
| Llama 3.3 70B InstructMeta | 45.2 GB · Too big | 77.7 GB · Too big | 143.8 GB · Too big |
| Mixtral 8x7B Instruct v0.1Mistral AI | 27.5 GB · Too big | 50.7 GB · Too big | 94.5 GB · Too big |
| Recursive FlintRecursive | 25.3 GB · Too big | 42.5 GB · Too big | 79.8 GB · Too big |
Each cell is the Hugging Face GGUF file size plus FP16 KV cache for an 8K-token context (or the model's maximum, if shorter). Fits = under 90% of 24 GB; Tight = 90 to 100%; Too big = over 24 GB. * = KV cache not included (no config data). Same data as the VRAM calculator and what can I run with 24 GB. Data checked 2026-10-30.
More for 24 GB cards
- RTX 4090 fit table and measured 4090 vs 3090 speed: same 24 GB, so the same models fit
- Everything that fits in 24 GB, including image generation and gaming
- Best GPUs for local LLMs: 24 GB, with specs from NVIDIA and AMD
- Run a MoE model bigger than your VRAM with expert offload to system RAM
- VRAM calculator for other context lengths
Rent a GPU
- Rent on Vast.ai Affiliate partner
- Rent on Runpod Referral
Hourly prices for the same GPU on both are on the GPU cost per hour page.
Some links on this page are affiliate or referral links: we may get a commission or account credit if you sign up. See our disclosure.
Too big for your card? Rent the VRAM by the hour, or upgrade.
Run it on a cloud GPU
No upgrade needed
Rent a 24–80 GB GPU for the hour you need it.
Vast.ai 
Runpod 
E2E Networks Buy this GPU
Own the VRAM
Compare current GPU prices first on our GPU price table and measured speeds.
We may earn from links marked Affiliate partner. Disclosure.