Can I Run Mistral Small 3 24B Instruct on 2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM)?
Full VRAM footprint analysis, tokens/sec generation benchmark, and copy-paste Ollama & vLLM runtime commands for running Mistral Small 3 24B Instruct (24B) on 2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM) (48 GB).
✓ Fits Comfortably in VRAM
Local Hardware Configurations & Pricing
NVIDIA GeForce RTX 5090 (32GB GDDR7)
Maximum tokens/sec on 27B–35B models & Blackwell FP4 quantization
NVIDIA GeForce RTX 4090 (24GB GDDR6X)
The 24GB CUDA enthusiast standard for 14B–32B Q4_K_M models
2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM)
Best price-to-VRAM homelab rig for Llama 3.3 70B Q4_K_M & Qwen 2.5 Coder 32B Q8_0
NVIDIA GeForce RTX 5080 (16GB GDDR7)
Blazing fast 8B–14B coding models with FP4/Q6_K precision
Cloud Instance Options for Mistral Small 3 24B Instruct
On-DemandDeploy this model on an on-demand cloud GPU without local hardware constraints or power usage:
Quantization Precision Matrix
32K ctx • KV: Q8_0| Quantization | Weights | KV Cache | Total VRAM | Est. Speed | Fit Status |
|---|---|---|---|---|---|
| FP1616 bpw | 48 GB | 2.68 GB | 53.81 GB (112%) | ~5 t/s | PARTIAL |
| Q8_08.5 bpw | 25.44 GB | 2.68 GB | 30.46 GB (63%) | ~39 t/s | FITS |
| Q6_K6.56 bpw | 19.68 GB | 2.68 GB | 24.5 GB (51%) | ~50 t/s | FITS |
| Q5_K_M5.68 bpw | 17.04 GB | 2.68 GB | 21.77 GB (45%) | ~58 t/s | FITS |
| Q4_K_M4.8 bpw | 14.4 GB | 2.68 GB | 19.03 GB (40%) | ~68 t/s | FITS |
| FP44.25 bpw | 12.72 GB | 2.68 GB | 17.3 GB (36%) | ~76 t/s | FITS |
| IQ3_XS3.3 bpw | 9.84 GB | 2.68 GB | 14.31 GB (30%) | ~97 t/s | FITS |
Frequently Asked Questions: Mistral Small 3 24B Instruct on 2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM)
How much VRAM does Mistral Small 3 24B Instruct need on 2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM)?
At standard 4-bit quantization (Q4_K_M) with 32K context, Mistral Small 3 24B Instruct requires 19.03 GB of total VRAM (weights + KV cache + CUDA runtime overhead).
What inference speed will Mistral Small 3 24B Instruct achieve on 2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM)?
Based on 2x NVIDIA RTX 3090 Dual Rig (48GB Total VRAM)'s 1648 GB/s memory bandwidth, expected decode speed is approximately 68 tokens per second.
Can I expand context beyond 32K tokens?
Each additional 32K tokens of context requires additional KV cache memory. For longer context windows, consider 8-bit or 4-bit KV cache quantization.