Skip to content
Run LLM Locally

Qwen3 8B on the RX 7900 GRE

With 16 GB of VRAM, the RX 7900 GRE runs Qwen3 8B at Q4_K_M entirely on the GPU with an 8K context (about 7 GB needed). At Q8_0 it fits entirely.

ShareFacebookXWhatsAppLinkedInEmail

Qwen3 8B

Q4_K_M · 8K context

Excellent

The model needs about 7 GB and fits in the 15.5 GB available, with 8.5 GB to spare.

Your hardware
RX 7900 GRE 16 GB · 64 GB RAM
Estimated memory
~7 GB estimate
VRAM (usable memory)
15.5 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
57–85 tok/s estimate
Largest context in fast memory
65K tokens
Confidence: low

Based on: memory bandwidth (576 GB/s) and model size

Memory breakdown

~7 GB (6.5 GB–7.5 GB) needed · estimate

Fits entirely in VRAM · 8.5 GB left

  • Model weights4.7 GB
  • KV cache1.1 GB
  • Runtime overhead0.9 GB
  • Safety margin0.3 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (ROCm) · flash attention on · weights = real file size

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

Other quantizations on the RX 7900 GRE

Qwen3 8B on RX 7900 GRE + 64 GB RAM · 8K context
Qwen3 8B Q8_08K~10.6 GB · 38–54 tok/s estimateExcellent
Qwen3 8B Q6_K8K~8.7 GB · 46–67 tok/s estimateExcellent
Qwen3 8B Q5_K_M8K~7.8 GB · 52–75 tok/s estimateExcellent
Qwen3 8B Q4_K_M8K~7 GB · 57–85 tok/s estimateExcellent
Qwen3 8B IQ4_XS8K~6.5 GB · 62–91 tok/s estimateExcellent
Qwen3 8B Q3_K_M8K~6.1 GB · 66–99 tok/s estimateExcellent

Alternatives

GPUs that run Qwen3 8B Q4_K_M entirely in VRAM

Other models that fit the RX 7900 GRE

Where to buy a RX 7900 GRE

Prices and links follow the market you choose.

Radeon RX 7900 GRE

16 GB GDDR6 · 576 GB/s · 260 W

ExcellentRuns Qwen3 8B Q4_K_M 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 7900 GRE run Qwen3 8B?
The model needs about 7 GB and fits in the 15.5 GB available, with 8.5 GB to spare.
Which quantization should I use on the RX 7900 GRE?
Q8_0 is the highest-precision quantization that fits entirely in VRAM at 8K context. ~10.6 GB / 15.5 GB.
What is the largest context on the RX 7900 GRE?
At Q4_K_M, about 65K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Qwen3 8B (RX 7900 GRE)?
We estimate 57–85 tok/s (estimate, confidence low). Based on: memory bandwidth (576 GB/s) and model size.