Can the Radeon RX 9070 XT Run Qwen3 8B?

Runs

Yes. Qwen3 8B at Q4_K_M is a 5 GB download (Hugging Face file listing for unsloth/Qwen3-8B-GGUF), and the Radeon RX 9070 XT has 16 GB of VRAM, leaving about 11 GB for the KV cache and runtime. Published runs put generation at a median of 90 tokens per second across 3 cited measurements. Fastest cited run: Vache Sarkissian (blog).

Model file5 GBQ4_K_M

VRAM16 GBRadeon RX 9070 XT

Headroom11 GBafter weights

Median speed90 tok/s3 cited runs

Bandwidth ceiling~128 tok/s645 GB/s ÷ 5 GB

Buy the Radeon RX 9070 XT

PowerColor Hellhound Spectral White AMD Radeon RX 9070 XT 16GB GDDR6

Tracked at $799 on 2026-08-28 — price may vary.

View Current Price →Details Used on eBay

Published runs for Qwen3 8B on the Radeon RX 9070 XT

Generation	Quant	Runtime	Context	Source	Date
100 tok/s	Q4_K_M	llama.cpp	—	Vache Sarkissian (blog)labelled "qwen3:8b"	2026-02-22
90 tok/s	q4_K_M	ollama	—	GitHub (hirokuze/local-llm-benchmark-rx9070xt)labelled "qwen3:8b"	2025-05-01
82.9 tok/s	Q4_K_M	ollama	—	Vache Sarkissian (blog)labelled "qwen3:8b"	2026-02-22

More about this pair

How much VRAM does Qwen3 8B need?

The Q4_K_M file is 5 GB. Add roughly 1.5 GB for the runtime and an ~8K-token context, so about 6.5 GB of VRAM holds it comfortably. Longer contexts grow the KV cache and need more.

What is the fastest Qwen3 8B can generate on the Radeon RX 9070 XT?

Generation reads every weight once per token, so the Radeon RX 9070 XT's 645 GB/s of memory bandwidth divided by the 5 GB file sets a ceiling near 128 tokens per second. Real runs land below it; SpecPicks rejects any published figure above it.

Check another pair

See the full matrix → · All Radeon RX 9070 XT benchmarks →

Qwen3 8B on other GPUs

RTX 4060 — Runs
RTX 3060 Ti — Runs
RTX 3060 12GB — Runs, 42 tok/s median
Intel Arc B580 — Runs, 24.2 tok/s median
RTX 4070 SUPER — Runs, 65.8 tok/s median
RTX 4060 Ti 16GB — Runs, 34.3 tok/s median
RTX 5060 Ti 16GB — Runs, 51.2 tok/s median
Intel Arc A770 16GB — Runs, 21 tok/s median
RTX 4070 Ti SUPER — Runs, 63.4 tok/s median
RTX 4080 — Runs, 77.9 tok/s median
RTX 5070 Ti — Runs, 121 tok/s median
RTX 5080 — Runs, 94.1 tok/s median
RTX 3090 — Runs, 101 tok/s median
Radeon RX 7900 XTX — Runs
RTX 4090 — Runs
RTX 5090 — Runs, 186 tok/s median
RTX A6000 48GB — Runs
RTX PRO 6000 Blackwell 96GB — Runs

Other models on the Radeon RX 9070 XT

Llama 3.2 1B — Runs
Llama 3.2 3B — Runs
Mistral 7B — Runs
Qwen2.5 7B — Runs
Llama 3.1 8B — Runs
DeepSeek-R1-Distill-Llama 8B — Runs
Gemma 2 9B — Runs
Gemma 3 12B — Runs
Qwen2.5 14B — Runs
DeepSeek-R1-Distill-Qwen 14B — Runs
Qwen3 14B — Runs, 50.1 tok/s median
Phi-4 14B — Runs
gpt-oss-20b — Runs, 91.9 tok/s median
Gemma 3 27B — Offload
Gemma 2 27B — Offload
Qwen3 30B-A3B — Offload
Qwen3 32B — Offload
Qwen2.5 32B — Offload
DeepSeek-R1-Distill-Qwen 32B — Offload
Llama 3.1 70B — Offload
Llama 3.3 70B — Offload
DeepSeek-R1-Distill-Llama 70B — Offload

How the checks work

The fit is the Q4_K_M file size against the card's VRAM, with 1.5 GB kept for the runtime and an ~8K context. A published run counts only if the pair fits, the run is Q4-class, its source does not call it an estimate, it is under the bandwidth ceiling above, and it is not one figure pasted across many cards. The whole matrix is downloadable as a CSV under CC BY 4.0.

As an Amazon Associate, SpecPicks earns from qualifying purchases.

This page is editorial synthesis based on publicly available information. No independent first-party benchmarking is reported.