Deploy GPU ↗
HARDWARE FIT CHECK • Mistral Small 3 24B Instruct + AMD Radeon RX 7900 XTX (24GB GDDR6)18.33 GB / 24 GB VRAM

Can I Run Mistral Small 3 24B Instruct on AMD Radeon RX 7900 XTX (24GB GDDR6)?

Full VRAM footprint analysis, tokens/sec generation benchmark, and copy-paste Ollama & vLLM runtime commands for running Mistral Small 3 24B Instruct (24B) on AMD Radeon RX 7900 XTX (24GB GDDR6) (24 GB).

✓ FITS IN VRAM18.33 GB (76%)~37 t/s

Target Hardware & Model

interactive
High-throughput Apache 2.0 dense model matching 70B performance, ideal for single 24GB GPUs (RTX 4090/3090/5090) at FP8/Q8
Mistral Small 3 24B Instruct on AMD Radeon RX 7900 XTX (24GB GDDR6)

✓ Fits Comfortably in VRAM

✓ FITS IN VRAM
Required VRAM
18.33 GB
76% of hardware capacity (24 GB)
Est. Decode Speed
~37 tok/s
Dense model @ 960 GB/s
Available Headroom
+5.67 GB
Safe for OS display & full context
Memory Allocation & Headroom
18.33 GB allocated of 24 GB capacity
76% utilized
Weights: 14.4 GB
KV: (32K): 2.68 GB
Overhead: 1.25 GB
Free Headroom: +5.67 GB
Architecture & Throughput Transparency: Single-user decode speed (~37 tok/s) is memory-bandwidth bound at batch size = 1 on AMD Radeon RX 7900 XTX (24GB GDDR6) (960 GB/s). Prompt prefill / TTFT (~537 tok/s) is compute-bound and utilizes GPU Tensor cores. Actual latency varies with FlashAttention-2 and runtime engine (Ollama/vLLM/llama.cpp).

Local Hardware Configurations & Pricing

High-bandwidth VRAM specs and current market prices
Consumer GPU
32 GB VRAM

NVIDIA GeForce RTX 5090 (32GB GDDR7)

Maximum tokens/sec on 27B–35B models & Blackwell FP4 quantization

1792 GB/s575W TDP
$1,999Amazon Prime →
Consumer GPU
24 GB VRAM

NVIDIA GeForce RTX 4090 (24GB GDDR6X)

The 24GB CUDA enthusiast standard for 14B–32B Q4_K_M models

1008 GB/s450W TDP
$1,699Amazon Prime →
Multi-GPU Rig
48 GB VRAM

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

1648 GB/s700W TDP
$1,550Amazon Prime →
Consumer GPU
24 GB VRAM

AMD Radeon RX 7900 XTX (24GB GDDR6)

Cheapest 24GB brand-new GPU for ROCm / Ollama on Linux

960 GB/s355W TDP
$899Amazon Prime →

Cloud Instance Options for Mistral Small 3 24B Instruct

On-Demand

Deploy this model on an on-demand cloud GPU without local hardware constraints or power usage:

RunPod Cloud GPUsBest 1-Click Ollama & vLLM
$0.38/hr (RTX 4090 Spot) – $2.39/hr (H100)
Launch 1-Click GPU Pod →
Vast.ai GPU MarketplaceCheapest Dual RTX 3090 / 4090
$0.18/hr (RTX 3060) – $0.78/hr (2x RTX 3090)
Rent Spot GPU →
Lambda GPU CloudEnterprise 8x H100 Clusters
$2.49/hr (H100) – $19.92/hr (8x H100)
Check H100 Availability →

Quantization Precision Matrix

32K ctx • KV: Q8_0
QuantizationWeightsKV CacheTotal VRAMEst. SpeedFit Status
FP1616 bpw48 GB2.68 GB53.11 GB (221%)0 t/sOOM
Q8_08.5 bpw25.44 GB2.68 GB29.76 GB (124%)~5 t/sPARTIAL
Q6_K6.56 bpw19.68 GB2.68 GB23.8 GB (99%)~27 t/sFITS
Q5_K_M5.68 bpw17.04 GB2.68 GB21.07 GB (88%)~31 t/sFITS
Q4_K_M4.8 bpw14.4 GB2.68 GB18.33 GB (76%)~37 t/sFITS
FP44.25 bpw12.72 GB2.68 GB16.6 GB (69%)~42 t/sFITS
IQ3_XS3.3 bpw9.84 GB2.68 GB13.61 GB (57%)~53 t/sFITS
FAQ & Reference

Frequently Asked Questions: Mistral Small 3 24B Instruct on AMD Radeon RX 7900 XTX (24GB GDDR6)

How much VRAM does Mistral Small 3 24B Instruct need on AMD Radeon RX 7900 XTX (24GB GDDR6)?

At standard 4-bit quantization (Q4_K_M) with 32K context, Mistral Small 3 24B Instruct requires 18.33 GB of total VRAM (weights + KV cache + CUDA runtime overhead).

What inference speed will Mistral Small 3 24B Instruct achieve on AMD Radeon RX 7900 XTX (24GB GDDR6)?

Based on AMD Radeon RX 7900 XTX (24GB GDDR6)'s 960 GB/s memory bandwidth, expected decode speed is approximately 37 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.