hipfire-LFM2.5-1.2B-Thinking

License: LFM Open License v1.0 — the LICENSE file in this repo is copied verbatim from LiquidAI/LFM2.5-1.2B-Thinking. This is a quantized derivative of a model created and released by Liquid AI; all upstream attribution and license terms apply.

hipfire-native Q8 quantization of LiquidAI/LFM2.5-1.2B-Thinking — the reasoning variant of LFM2.5-1.2B. Same hybrid edge architecture: 16 layers (10 gated short-conv + 6 GQA full-attention, 32 q heads / 8 kv heads), hidden 2048, SwiGLU FFN 12288, vocab 65536, 128K context. Emits <think>…</think> reasoning before the final answer.

The .q8 file runs with the hipfire inference engine (HIP/ROCm-direct, Rust, no Python in the hot path). It is not GGUF/safetensors and won't load in llama.cpp / transformers. All weights are stored at Q8 and dequantized to f32 on the fly inside the GEMV kernels.

Files

File	Quant	Size
lfm2.5-1.2b-thinking.q8	Q8 (all tensors)	1.25 GB

The LiquidAI chat template is embedded in the file and used by default (jinja chat is default-on in hipfire; opt out with HIPFIRE_JINJA_CHAT=0). The template strips past-turn <think> blocks from history by default (keep_past_thinking=false), matching upstream behavior.

Usage (hipfire)

# hipfire CLI (registry tag, once available in your hipfire version):
hipfire pull lfm2.5:1.2b-thinking
hipfire run lfm2.5:1.2b-thinking "What is the capital of France?"

# or download directly and point at the file:
hf download hipfire-models/hipfire-LFM2.5-1.2B-Thinking lfm2.5-1.2b-thinking.q8 --local-dir ~/.hipfire/models
hipfire serve --model ~/.hipfire/models/lfm2.5-1.2b-thinking.q8

Give it headroom: reasoning turns typically need a few hundred tokens of max_tokens before the final answer appears after </think>.

Validation

Greedy (temperature 0.0) daemon transcript on RDNA3 (gfx1100 / RX 7900 XTX), hipfire v0.2.1:

prompt: "What is the capital of France?"
output: "<think> Okay, let's see. The question is asking "What is the capital
         of France?" … The capital of France is indeed Paris. The Eiffel Tower
         is there, the Louvre Museum, Notre-Dame Cathedral… </think>
         The capital of France is **Paris**.
         Paris serves as the country's political, cultural, and economic
         center, renowned for landmarks like the Eiffel Tower, Louvre Museum,
         and Notre-Dame Cathedral.
         **Answer:** The capital of France is Paris."
~395 tok/s decode, 45 ms prefill

Known cosmetic nit: at the very end of a greedy completion the model may emit a short run of byte-fallback tokens (an emoji) that stream as � replacement characters in clients that decode token-by-token; the answer text itself is unaffected.

arch_id 11 in the hipfire HFQ header.