TokenAssemble

AMD GPU

AMD Radeon RX 9070

The AMD Radeon RX 9070 has 16GB of VRAM and 640 GB/s of memory bandwidth. Its sweet spot tops out around gpt-oss-20b — the largest model that loads cleanly at a quality quant with llama.cpp at 8K context.

AMD verdicts are beta: fit is physics and holds, but ROCm/Vulkan speed tiers aren't calibrated yet — treat tiers as provisional until real measurements land.
VRAM
16 GB
Memory bandwidth
640 GB/s
TDP
220 W
MSRP
$549
Backends
ROCm · Vulkan

Specs as of 2026-07-08 · source

Affiliate link — we may earn a commission. Verdicts are computed before any link is attached.

What an AMD Radeon RX 9070 can run

Every model we track, graded at its best clean-fit quant. Click any verdict for the full breakdown.

ModelBest-quant verdict · llama.cpp · 8K context
Qwen3-8BFits · A+ · Q8_0interactivebeta
gemma-4-26B-A4B-itTight · C · MXFP4_MOEinteractive · offloadbeta
Qwen2.5-7B-InstructFits · A+ · Q8_0interactivebeta
Qwen2.5-1.5B-InstructFits · A+ · Q8_0interactivebeta
Llama-3.2-1B-InstructFits · A+ · Q8_0interactivebeta
Llama-3.1-8B-InstructFits · A+ · Q8_0interactivebeta
DeepSeek-R1Won't fitbeta
Qwen3.5-9BFits · B · Q8_0interactivebeta
gpt-oss-20bFits · B · MXFP4interactivebeta
Qwen3.6-35B-A3BTight · C · MXFP4_MOEinteractive · offloadbeta
Qwen2.5-3B-InstructFits · A+ · Q8_0interactivebeta
Qwen3-32BTight · C · Q4_K_Musable · offloadbeta
Qwen3.6-27BTight · C · Q4_K_Musable · offloadbeta
Qwen2.5-0.5B-InstructFits · A+ · Q8_0interactivebeta
Mistral-7B-Instruct-v0.3Fits · A+ · Q8_0interactivebeta
gpt-oss-120bTight · C · MXFP4interactive · offloadbeta
Qwen3-14BFits · B · Q5_K_Minteractivebeta
Qwen3-30B-A3BTight · C · Q4_K_Minteractive · offloadbeta
Qwen2.5-32B-InstructTight · C · Q4_K_Musable · offloadbeta
DeepSeek-V4-FlashWon't fitbeta
Qwen2.5-14B-InstructFits · B · Q5_K_Minteractivebeta
Llama-3.2-3B-InstructFits · A+ · Q8_0interactivebeta
gemma-3-4b-itFits · A+ · Q8_0interactivebeta
gemma-3-12b-itFits · B · Q6_Kinteractivebeta
Llama-3.1-70B-InstructTight · C · Q4_K_Mpainful · offloadbeta
Phi-3.5-mini-instructFits · A+ · Q8_0interactivebeta
Phi-4Fits · B · Q5_K_Minteractivebeta
DeepSeek-R1-Distill-Qwen-32BTight · C · Q4_K_Musable · offloadbeta
gemma-3-27b-itTight · C · Q4_K_Musable · offloadbeta
Llama-3.3-70B-InstructTight · C · Q4_K_Mpainful · offloadbeta
Qwen2.5-72B-InstructTight · C · Q4_K_Mpainful · offloadbeta
gemma-2-2b-itFits · A+ · Q8_0interactivebeta
DeepSeek-R1-Distill-Qwen-14BFits · B · Q5_K_Minteractivebeta
DeepSeek-R1-Distill-Llama-8BFits · A+ · Q8_0interactivebeta
DeepSeek-R1-Distill-Qwen-7BFits · A+ · Q8_0interactivebeta
gemma-2-9b-itFits · B · Q8_0interactivebeta
Mistral-Nemo-Instruct-2407Fits · B · Q6_Kinteractivebeta
QwQ-32BTight · C · Q4_K_Musable · offloadbeta
Mistral-Small-24B-Instruct-2501Tight · C · Q4_K_Musable · offloadbeta
gemma-2-27b-itTight · C · Q4_K_Musable · offloadbeta

Verdicts computed from published specs and measured GGUF sizes — how the math works.