Skip to content
Run LLM Locally

Olmo 3.1 32B Instruct on the RX 7900 XTX

With 24 GB of VRAM, the RX 7900 XTX runs Olmo 3.1 32B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 21.2 GB needed). At Q8_0 it does not fit in VRAM.

ShareFacebookXWhatsAppLinkedInEmail

Olmo 3.1 32B Instruct

Q4_K_M · 8K context

Compatible

The model needs about 21.2 GB and fits in the 23.3 GB available (2.1 GB left).

Your hardware
RX 7900 XTX 24 GB · 64 GB RAM
Estimated memory
~21.2 GB estimate
VRAM (usable memory)
23.3 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
28–40 tok/s estimate
Largest context in fast memory
40K tokens
Confidence: low

Based on: memory bandwidth (960 GB/s) and model size

Memory breakdown

~21.2 GB (20.5 GB–21.9 GB) needed · estimate

Fits entirely in VRAM · 2.1 GB left

  • Model weights18.1 GB
  • KV cache1.3 GB
  • Runtime overhead0.8 GB
  • Safety margin1 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (ROCm) · flash attention on · weights = real file size · sliding-window layers keep 4,096 tokens

EstimateData updated 40 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 XTX

Olmo 3.1 32B Instruct on RX 7900 XTX + 64 GB RAM · 8K context
Olmo 3.1 32B Instruct Q8_08K~35.6 GB · 1.5–3 tok/s estimatePossible but slow
Olmo 3.1 32B Instruct Q6_K8K~28 GB · 3.5–7 tok/s estimateCPU/GPU offload
Olmo 3.1 32B Instruct Q5_K_M8K~24.5 GB · 9.5–18 tok/s estimateCPU/GPU offload
Olmo 3.1 32B Instruct Q4_K_M8K~21.2 GB · 28–40 tok/s estimateCompatible
Olmo 3.1 32B Instruct IQ4_XS8K~19.1 GB · 30–45 tok/s estimateExcellent
Olmo 3.1 32B Instruct Q3_K_M8K~17.4 GB · 33–49 tok/s estimateExcellent

Alternatives

GPUs that run Olmo 3.1 32B Instruct Q4_K_M entirely in VRAM

Other models that fit the RX 7900 XTX

Where to buy a RX 7900 XTX

Prices and links follow the market you choose.

Radeon RX 7900 XTX

24 GB GDDR6 · 960 GB/s · 355 W

CompatibleRuns Olmo 3.1 32B Instruct 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 XTX run Olmo 3.1 32B Instruct?
The model needs about 21.2 GB and fits in the 23.3 GB available (2.1 GB left).
Which quantization should I use on the RX 7900 XTX?
Q4_K_M is the highest-precision quantization that fits entirely in VRAM at 8K context. ~21.2 GB / 23.3 GB.
What is the largest context on the RX 7900 XTX?
At Q4_K_M, about 40K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Olmo 3.1 32B Instruct (RX 7900 XTX)?
We estimate 28–40 tok/s (estimate, confidence low). Based on: memory bandwidth (960 GB/s) and model size.