view post Post 218 I did some testing on the scalability of FWKV. It hits a speed bottleneck at 1B due to the T4’s bandwidth limitations. Theoretically, it should match RWKV’s inference speed if the GPU had more bandwidth. So the 1B size is not accurate. See translation
My LFM2 fine-tunes Here i would the LFM2 fine tunes that i am proud of. FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 Text Generation • 1B • Updated about 19 hours ago • 556 • 2 FlameF0X/LFM2.5-1.2B-Distilled-Claude Text Generation • 1B • Updated 6 days ago • 72 • 1 FlameF0X/LFM2.5-1.2B-Thinking-CodeX Text Generation • 1B • Updated about 19 hours ago • 414 • 1
FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 Text Generation • 1B • Updated about 19 hours ago • 556 • 2
FWKV FlameF0X/FWKV-50M Text Generation • 50.6M • Updated 14 days ago • 136 Running Agents FWKV 50M Demo 🦀 Generate AI-written text continuations from a prompt FlameF0X/FWKV-29M Text Generation • 28.9M • Updated 19 days ago • 266 FlameF0X/FWKV-TinyStories Text Generation • Updated 18 days ago • 1
My LFM2 fine-tunes Here i would the LFM2 fine tunes that i am proud of. FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 Text Generation • 1B • Updated about 19 hours ago • 556 • 2 FlameF0X/LFM2.5-1.2B-Distilled-Claude Text Generation • 1B • Updated 6 days ago • 72 • 1 FlameF0X/LFM2.5-1.2B-Thinking-CodeX Text Generation • 1B • Updated about 19 hours ago • 414 • 1
FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 Text Generation • 1B • Updated about 19 hours ago • 556 • 2
FWKV FlameF0X/FWKV-50M Text Generation • 50.6M • Updated 14 days ago • 136 Running Agents FWKV 50M Demo 🦀 Generate AI-written text continuations from a prompt FlameF0X/FWKV-29M Text Generation • 28.9M • Updated 19 days ago • 266 FlameF0X/FWKV-TinyStories Text Generation • Updated 18 days ago • 1
pinned Running on Zero Agents TerraLM - AI Plays Terraria 🌍 Watch an AI (TerraLM-350M) play a bare-minimum Terraria!
FlameF0X/LFM2.5-1.2B-Distilled-Claude-4.6 Text Generation • 1B • Updated about 19 hours ago • 556 • 2