No. gpt-oss-120b does not fit on the Radeon RX 7900 XTX at Q4. The estimate is 63.1 GB and usable memory is 22.8 GB.
Can the Radeon RX 7900 XTX run gpt-oss-120b?
Data updated . Last reviewed the same day, when this catalog snapshot was written.
Usable memory on this 24 GB VRAM config is 22.8 GB (95% of the sticker figure). A result under 2 GB of headroom is labeled tight.
Quant ladder
| Quant | Estimate | Headroom | Est. tok/s | Verdict |
|---|---|---|---|---|
| Q4 | 63.1 GB | -40.3 GB | 350 tok/s | No |
| Q8 | 63.7 GB | -40.9 GB | 347 tok/s | No |
| FP16 | 280 GB | -257.6 GB | 94.1 tok/s | No |
- GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
- Formula estimate: parameter count × bytes per weight × 1.20. No GGUF file size is stored for this quant.
- Tokens/sec is a bandwidth roofline: GB/s divided by active weight GB. It is not a measured generation speed.
KV cache at 8K and 32K
FP16 KV-cache estimate: 0.3 GB at 8,192 tokens and 1.2 GB at 32,768 tokens. GQA counts two tensors (K and V) for the stored KV heads and head dimension. config.json also sets a sliding window of 128 tokens. The figures above assume every counted layer stores the full context, so they can overstate cache on sliding layers.
Offload
About 40.0 GB of the Q4 weights sit outside usable VRAM. A partial offload would need at least that much free system RAM. This catalog does not record system RAM, so offload is not counted as a fit.
Ollama
This command pulls the Q4_K_M file from unsloth/gpt-oss-120b-GGUF, the Hub repo whose file size is used above. It is not an official Ollama library tag.
ollama run hf.co/unsloth/gpt-oss-120b-GGUF:Q4_K_M
What fits instead
- Cheapest catalog device at Q4: Framework Desktop 128GB
- Closest catalog model that still fits at Q4: Qwen3.6 35B-A3B.
All hardware for gpt-oss-120b · All models for the Radeon RX 7900 XTX
Questions
- How much memory does gpt-oss-120b need at Q4?
- The Q4 figure used here is 63.1 GB. GGUF file size plus an FP16 KV-cache estimate at 8,192 tokens. The cache counts only the layers and heads named in the method on the About page.
- Can the Radeon RX 7900 XTX run gpt-oss-120b?
- No. gpt-oss-120b does not fit on the Radeon RX 7900 XTX at Q4. The estimate is 63.1 GB and usable memory is 22.8 GB.
- What is the cheapest catalog device that runs gpt-oss-120b at Q4?
- Framework Desktop 128GB, list price $3,449.
- How fast is gpt-oss-120b on the Radeon RX 7900 XTX, as a bandwidth estimate?
- About 350 tok/s at Q4. That is device bandwidth divided by active weight bytes, not a measured run.