LFM2.5-8B-A1B-JANG_2L
JANG_2L conversion of LiquidAI/LFM2.5-8B-A1B, built for Apple Silicon inference through JANG-aware MLX/vMLX runtimes.
This bundle is not a plain MLX 2-bit quant. It uses JANG importance allocation over MLX affine quantized tensors, with higher precision reserved for runtime-sensitive tensors.
Format
- Format: JANG affine
- Profile:
JANG_2L - Quantization backend:
mx.quantize - Group size:
64 - Actual bits from
jang_config.json:2.37 - Bit widths used:
2,6,8 - Passthrough bit width:
16 - Local size before upload:
2.9G - JANG runtime weight size metadata:
2.84 GB - Source model:
LiquidAI/LFM2.5-8B-A1B
Runtime capability stamp:
{
"reasoning_parser": "qwen3",
"tool_parser": "lfm2",
"think_in_template": false,
"supports_tools": true,
"supports_thinking": true,
"family": "lfm2_moe",
"modality": "text",
"cache_type": "hybrid"
}
Runtime
Use a JANG-aware MLX/vMLX runtime. The model has hybrid cache behavior: attention layers use KV cache, while LIV convolution layers use convolution/state cache.
Example with the local JANG tools runtime:
python -m jang_tools inference \
--model OsaurusAI/LFM2.5-8B-A1B-JANG_2L \
--prompt "What is 2+2? Answer briefly." \
--max-tokens 128 \
--temperature 0
Chat Template And Reasoning
The bundled chat_template.jinja uses Liquid's ChatML-like format:
- User and assistant turns use
<|im_start|>/<|im_end|>. - The generation prompt ends at
<|im_start|>assistant\n; it does not pre-open<think>. - Assistant reasoning may appear inside
<think>...</think>. - Tool calls use Liquid's Python-call list format inside
<|tool_call_start|>and<|tool_call_end|>.
For this bundle, think_in_template=false is intentional. Runtime code should parse reasoning if the model emits it, but should not force a second reasoning prefix.
Verification
Local smoke run on the converted bundle:
- Prompt:
What is 2+2? Answer briefly. - Result: output closed
<think>...</think>and answered2 + 2 = 4. - Reported generation speed:
206.886 tok/s - Load time:
1.946 s - Peak RSS:
3887 MB
This is a smoke test, not a benchmark suite or accuracy evaluation.
Korean
이 모델은 LiquidAI/LFM2.5-8B-A1B를 JANG_2L 형식으로 변환한 Apple Silicon용 번들입니다. think_in_template=false가 의도된 설정이며, 런타임은 모델이 생성한 <think>...</think>를 파싱하되 별도의 reasoning 접두어를 강제로 추가하지 않아야 합니다.