readygpu

LFM2.5 8B-A1B

8.5B total, 1B active · 125k context · lfm1.0 · released 2026-05-28

chat

What to run it on in Germany

Fully in memory at 128k context, priced at retailers today.

Something we price holds it fully in memory, but none reaches 15 tok/s, our bar for recommending it. The table below has the speeds.

All hardware that runs it

Everything we price, best value first. Two cards split the model by layers.

HardwareQuantFitsDecodePricetok/s per 1,000
NVIDIA GeForce RTX 3090Q8_0fits46 tok/s––
NVIDIA GeForce RTX 5090Q8_0fits89 tok/s––
Mac Studio M4 Max 128GBQ8_0fits28 tok/s––
NVIDIA GeForce RTX 4090Q8_0fits50 tok/s––
NVIDIA GeForce RTX 5070 TiUD-Q6_Kfits46 tok/s––
Mac mini M4 Pro 64GBQ8_0fits14 tok/s––
NVIDIA GeForce RTX 5060 Ti 16GBUD-Q6_Kfits23 tok/s––
AMD Radeon RX 7900 XTXQ8_0fits42 tok/s––
Framework Desktop Ryzen AI Max+ 395 128GBQ8_0fits11 tok/s––
Mac Studio M3 Ultra 512GBQ8_0fits43 tok/s––
NVIDIA DGX Spark 128GBQ8_0fits14 tok/s––
AMD Radeon RX 9070 XTUD-Q6_Kfits29 tok/s––
GMKtec EVO-X2 Ryzen AI Max+ 395 128GBQ8_0fits11 tok/s––
Mac Studio M3 Ultra 256GBQ8_0fits43 tok/s––
Mac mini M4 Pro 48GBQ8_0fits14 tok/s––
NVIDIA GeForce RTX 4060 Ti 16GBUD-Q6_Kfits15 tok/s––
NVIDIA GeForce RTX 5080UD-Q6_Kfits49 tok/s––
Mac Studio M4 Max 64GBQ8_0fits28 tok/s––
NVIDIA GeForce RTX 4070 Ti SuperUD-Q6_Kfits34 tok/s––
AMD Radeon RX 9060 XT 16GBUD-Q6_Kfits15 tok/s––
Mac Studio M3 Ultra 96GBQ8_0fits43 tok/s––
NVIDIA GeForce RTX 4080 SuperUD-Q6_Kfits38 tok/s––
NVIDIA RTX PRO 6000 BlackwellQ8_0fits89 tok/s––
AMD Radeon AI PRO R9700Q8_0fits28 tok/s––
AMD Radeon RX 7800 XTUD-Q6_Kfits28 tok/s––
AMD Radeon RX 7900 XTQ8_0fits35 tok/s––
ASUS Ascent GX10 128GBQ8_0fits14 tok/s––
Framework Desktop Ryzen AI Max+ 395 64GBQ8_0fits11 tok/s––
Mac mini M4 32GBQ8_0fits6 tok/s––
NVIDIA GeForce RTX 3090 TiQ8_0fits50 tok/s––
AMD Radeon RX 7600 XTUD-Q6_Kfits13 tok/s––
Intel Arc Pro B60Q8_0fits17 tok/s––
NVIDIA Tesla P40Q8_0fits17 tok/s––
Intel Arc A770 16GBUD-Q6_Kfits21 tok/s––
NVIDIA GeForce RTX 3060 12GBUD-Q4_K_Moffload15 tok/s––
NVIDIA GeForce RTX 5070UD-Q4_K_Moffload22 tok/s––
NVIDIA GeForce RTX 4070 SuperUD-Q4_K_Moffload18 tok/s––
Intel Arc B580UD-Q4_K_Moffload13 tok/s––
NVIDIA GeForce RTX 3080 10GBUD-Q4_K_Moffload13 tok/s––

1 other card or machine we price cannot hold it at this context.

Memory needed

Weights, KV cache and runtime buffers at each context length (KV cache at fp16).

QuantFile@8k@32k@64k
UD-Q4_K_Mgguf5.0 GB6.1 GB7.3 GB9.0 GB
UD-Q5_K_Mgguf5.9 GB7.0 GB8.3 GB10.0 GB
UD-Q6_Kgguf6.6 GB7.7 GB9.0 GB10.7 GB
Q8_0gguf8.4 GB9.5 GB10.8 GB12.5 GB

Run it

Copy a command for the runtime you use.

  • UD-Q4_K_M
    • Ollamaollama run hf.co/unsloth/LFM2.5-8B-A1B-GGUF:UD-Q4_K_M
    • LM Studiolms get unsloth/LFM2.5-8B-A1B-GGUF@ud-q4_k_m
    • llama.cppllama-server -hf unsloth/LFM2.5-8B-A1B-GGUF:UD-Q4_K_M
  • UD-Q5_K_M
    • Ollamaollama run hf.co/unsloth/LFM2.5-8B-A1B-GGUF:UD-Q5_K_M
    • LM Studiolms get unsloth/LFM2.5-8B-A1B-GGUF@ud-q5_k_m
    • llama.cppllama-server -hf unsloth/LFM2.5-8B-A1B-GGUF:UD-Q5_K_M
  • UD-Q6_K
    • Ollamaollama run hf.co/unsloth/LFM2.5-8B-A1B-GGUF:UD-Q6_K
    • LM Studiolms get unsloth/LFM2.5-8B-A1B-GGUF@ud-q6_k
    • llama.cppllama-server -hf unsloth/LFM2.5-8B-A1B-GGUF:UD-Q6_K
  • Q8_0
    • Ollamaollama run hf.co/unsloth/LFM2.5-8B-A1B-GGUF:Q8_0
    • LM Studiolms get unsloth/LFM2.5-8B-A1B-GGUF@q8_0
    • llama.cppllama-server -hf unsloth/LFM2.5-8B-A1B-GGUF:Q8_0