GPU HUNTER/v0.7.0
BrowseCompareToolsResearchBlog
Find your GPU
GPU HUNTER

Community-sourced benchmark estimates and model-fit planning for engineers who run AI on their own hardware.

Dataset snapshot · Apr 30, 2026Static reference index
Hardware
  • All GPUs
  • Workstation
  • Consumer
  • Apple Silicon
Tools
  • All tools
  • VRAM calculator
  • GPU cost calculator
  • Watch planner
  • Compare GPUs
Resources
  • Blog
  • Research
  • Methodology
  • Editorial policy
  • llms.txt
  • Partnerships
  • Contact
© 2026 GPU HUNTER · Not affiliated with NVIDIA, AMD, or AppleSome links are affiliate links. We may earn a commission at no extra cost to you.Sponsorship inquiries · partnerships@gpuhunter.iov0.7.0 · dataset 2026.04.30
browse/amd/rx-7900-xtx
RR7
AMDConsumerAMD pick

Radeon RX 7900 XTX

RDNA 3 · TSMC 5nm + 6nm · released 2022-12

Best AMD consumer GPU for AI. 24GB at under $850. ROCm 7.2 finally delivers Ollama/llama.cpp parity.

VRAM
24 GB
Bandwidth
960 GB/s
TDP
355 W
8B Q4
66 t/s
Score
73 /100
Reference price
$849
MSRP $999 · ↓ 15%
Search Amazon listings Newegg
market data
Snapshot estimate · Apr 30, 2026
Not live
Affiliate link — we may earn a commission
01  //  Representative inference estimates

Single-stream decode · llama.cpp

Llama 8B · Q4_K_M
66 t/s
Llama 8B · Q8_0
40 t/s
Llama 8B · FP16
22 t/s
Aggregated from published community sources. Test setups differ, so use close results as directional evidence. Sources and normalization →
01b  //  Performance across quantization

vs. nearest competitors

How tok/s scales from FP16 → Q8 → Q4 compared to GPUs in a similar price/VRAM range.

02  //  Hardware specs
ArchitectureRDNA 3
Process nodeTSMC 5nm + 6nm
Memory24 GB
Memory bandwidth960 GB/s
FP16 compute61.4 TFLOPS
INT8 compute123 TOPS
TDP355 W
PCIeGen 4 x16
Form factorTriple-slot
CoolingAxial
03  //  Model fit

Weight estimate plus 15% planning headroom for runtime buffers and a modest KV cache. Long context can require more.

Qwen3 32B
128k ctx
Q4
22 GB
FITS
Q8
42 GB
NO
FP16
74 GB
NO
Qwen2.5 72B
128k ctx
Q4
51 GB
NO
Q8
90 GB
NO
FP16
167 GB
NO
Qwen3 235B-A22B
128k ctx
Q4
152 GB
NO
Q8
276 GB
NO
FP16
541 GB
NO
Llama 3.3 70B
128k ctx
Q4
46 GB
NO
Q8
87 GB
NO
FP16
161 GB
NO
DeepSeek V3
128k ctx
Q4
437 GB
NO
Q8
805 GB
NO
FP16
1495 GB
NO
Llama 3.1 8B
128k ctx
Q4
6 GB
FITS
Q8
11 GB
FITS
FP16
19 GB
FITS
Qwen3 14B
128k ctx
Q4
10 GB
FITS
Q8
18 GB
FITS
FP16
33 GB
NO
Mistral 7B
32k ctx
Q4
5 GB
FITS
Q8
10 GB
FITS
FP16
17 GB
FITS
Gemma 2 27B
8k ctx
Q4
19 GB
FITS
Q8
35 GB
NO
FP16
63 GB
NO
Codestral 22B
32k ctx
Q4
15 GB
FITS
Q8
28 GB
NO
FP16
51 GB
NO
+ STRENGTHS
  • ✓24GB clears our Qwen3 32B Q4 planning target
  • ✓960 GB/s memory bandwidth · top tier in its class
  • ✓Indexed formats: FP16, Q8, Q4 · verify support in your runtime
− TRADE-OFFS
  • −Draws 355W under load — plan PSU and thermals accordingly
  • −Limited to triple-slot chassis
  • −Driver lock-in to vendor stack
related research

Research behind Radeon RX 7900 XTX inference tradeoffs

These papers explain the quantization, cache, bandwidth, and runtime constraints that matter before buying this GPU for local AI.

GPU inference optimization papers

Memory bandwidth, FlashAttention, dequant kernels, and backend maturity.

Open
Local AI inference papers

llama.cpp, Apple Silicon, constrained GPUs, offload, and one-box inference.

Open
LLM serving systems papers

vLLM, PagedAttention, speculative decoding, batching, and GPU servers.

Open
04  //  You may also be considering
Open compare Model ownership cost Build watch plan
R3
GeForce RTX 3090
24GB · $749
vs
R3T
GeForce RTX 3090 Ti
24GB · $849
vs
R4T
GeForce RTX 4070 Ti SUPER
16GB · $699
vs