text model · LFM · Windows
Can I run LFM2 24B-A2B on AMD Radeon RX 7900 XTX (24GB)?
Yes. LFM2 24B-A2B runs on AMD Radeon RX 7900 XTX (24GB) at Q4_K_M (~15.4 GB of ~23 GB usable).
Runs at Q4_K_M using ~15.4 GB of ~23 GB usable.
That figure is at a 4k context and moves about ±15% as context length changes. AMD Radeon RX 7900 XTX (24GB) leaves ~7.6 GB of headroom.
- Q4_K_M needed
- ~15.4 GB
- Usable on device
- ~23 GB
- Device memory
- 24 GB
- Best quant
- Q4_K_M
Which quant fits
Run it
Pick your tool. All 3 load the same Q4_K_M weights.
ollama run lfm2:24b llama-cli -hf LiquidAI/LFM2-24B-A2B-GGUF:Q4_K_M lms get LiquidAI/LFM2-24B-A2B-GGUF - Parameters
- 24B (MoE, 2.3B active)
- Q4_K_M size
- 13.43 GB
- Q8_0 size
- 23.61 GB
- Context
- 32k
- Ollama tag
- lfm2:24b
- Memory
- 24 GB vram
- Usable for weights
- ~23 GB
- Power draw
- ~355 W
- Best runtime
- Ollama (ROCm) / llama.cpp ROCm (Linux)
You could also run
Run LFM2 24B-A2B on other hardware
FAQ
Can AMD Radeon RX 7900 XTX (24GB) run LFM2 24B-A2B?
Yes. LFM2 24B-A2B runs on AMD Radeon RX 7900 XTX (24GB) at Q4_K_M (~15.4 GB of ~23 GB usable).
How much memory does LFM2 24B-A2B need?
AMD Radeon RX 7900 XTX (24GB) has room to spare. At Q4_K_M the weights are ~13.43 GB; with KV cache and runtime overhead, budget ~15.4 GB at a 4k context. It is a Mixture-of-Experts model (24B total / 2.3B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run LFM2 24B-A2B on Windows?
LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
Embed this
A live badge for your model card or README, updated as the data is. [](https://localmodel.run/can-i-run/lfm2-24b-a2b/amd-rx-7900-xtx-24gb) Sources
Weights are measured from GGUF files; KV cache and overhead are computed, so totals can vary ~15% with context and runtime. Any tok/s is a bandwidth estimate. See methodology.