Can Strix Halo (Radeon 8060S) run LFM2.5 24B-A2B?

Q: Can Strix Halo (Radeon 8060S) run LFM2.5 24B-A2B?

Yes. Measured 100.2 tok/s generation on Strix Halo (Radeon 8060S), via llama.cpp (Vulkan), Unsloth UD-Q4_K_XL (13.9 GiB). Source: https://bryanlurer.com/posts/llm-bench/

Last updated: 9 Nov 2026

Yes. Measured 100.2 tok/s generation (llama.cpp (Vulkan), Unsloth UD-Q4_K_XL (13.9 GiB); source).

Every measured result for LFM2.5 24B-A2B on Strix Halo (Radeon 8060S)

Build	Quant / setup	Engine	tok/s
GMKtec EVO-X2 (Strix Halo 128 GB, quiet 54 W mode): Qwen3.8 Flash-Next UD-Q4_K_XL at 37.2 tok/s on Gufo ROCm (MTP), Qwen3.6 35B-A3B at 81.9 with MTP	Unsloth UD-Q4_K_XL (13.9 GiB)	llama.cpp (Vulkan)	100.2	source

Memory: Strix Halo (Radeon 8060S) has 128 GB. LFM2.5 24B-A2B weights are about 14.7 GB at Q4_K_M (23.97B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for LFM2.5 24B-A2B: best home rig for LFM2.5 24B-A2B.

LFM2.5 24B-A2B on other hardware: RTX 3060 12GB · RTX 4060 Ti 16GB · RTX 4090

Other models measured on Strix Halo (Radeon 8060S): Gemma 4 12B · Gemma 4 26B-A4B · Gemma 4 31B · Kolibri-1 · Qwen3.5 122B · Qwen3.5 9B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · Qwen3.8 Flash-Next · gpt-oss 120B · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run LFM2.5 24B-A2B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.