Skip to content
Run LLM Locally

gpt-oss-20b on the RX 7600 XT

With 16 GB of VRAM, the RX 7600 XT runs gpt-oss-20b at MXFP4 entirely on the GPU with an 8K context (about 12.9 GB needed).

ShareFacebookXWhatsAppLinkedInEmail

gpt-oss-20b

MXFP4 · 8K context

Excellent

The model needs about 12.9 GB and fits in the 15.5 GB available, with 2.6 GB to spare.

Your hardware
RX 7600 XT 16 GB · 64 GB RAM
Estimated memory
~12.9 GB estimate
VRAM (usable memory)
15.5 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
59–100 tok/s estimate
Largest context in fast memory
114K tokens
Confidence: low

Based on: memory bandwidth (288 GB/s) and model size

Memory breakdown

~12.9 GB (12.3 GB–13.5 GB) needed · estimate

Fits entirely in VRAM · 2.6 GB left

  • Model weights11.3 GB
  • KV cache0.2 GB
  • Runtime overhead0.8 GB
  • Safety margin0.6 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (Vulkan) · flash attention on · weights = real file size · sliding-window layers keep 128 tokens

EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • no benchmark for this hardware and model yet
  • mixture-of-experts: speed depends on expert routing

Other quantizations on the RX 7600 XT

gpt-oss-20b on RX 7600 XT + 64 GB RAM · 8K context
gpt-oss-20b MXFP48K~12.9 GB · 59–100 tok/s estimateExcellent

Alternatives

GPUs that run gpt-oss-20b MXFP4 entirely in VRAM

Other models that fit the RX 7600 XT

Where to buy a RX 7600 XT

Prices and links follow the market you choose.

Radeon RX 7600 XT

16 GB GDDR6 · 288 GB/s · 190 W

ExcellentRuns gpt-oss-20b MXFP4 entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the RX 7600 XT run gpt-oss-20b?
The model needs about 12.9 GB and fits in the 15.5 GB available, with 2.6 GB to spare.
Which quantization should I use on the RX 7600 XT?
MXFP4 is the highest-precision quantization that fits entirely in VRAM at 8K context. ~12.9 GB / 15.5 GB.
What is the largest context on the RX 7600 XT?
At MXFP4, about 114K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is gpt-oss-20b (RX 7600 XT)?
We estimate 59–100 tok/s (estimate, confidence low). Based on: memory bandwidth (288 GB/s) and model size.