LFM2.5-1.2B-Instruct-GGUF
LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
Params
1.2 B
Context
128,000
Downloads 30d
257 K
Likes
239
Download history
daily snapshots · 106 days
▲ 79 K in the last 30 days (23.5%)
350 K257 K
Oct 12Oct 22Nov 1Nov 10
356 K188 K
Aug 13Sep 12Oct 12Nov 10
356 K188 K
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf | Q4_0 | 0.7 GB | 1.4 GB | ✅ Runs comfortably |
| LFM2.5-1.2B-Instruct-Q4_K_M.gguf | Q4_K_M | 0.7 GB | 1.5 GB | ✅ Runs comfortably |
| LFM2.5-1.2B-Instruct-Q5_K_M.gguf | Q5_K_M | 0.8 GB | 1.6 GB | ✅ Runs comfortably |
| LFM2.5-1.2B-Instruct-Q6_K.gguf | Q6_K | 1.0 GB | 1.7 GB | ✅ Runs comfortably |
| LFM2.5-1.2B-Instruct-Q8_0.gguf | Q8_0 | 1.2 GB | 2.1 GB | ✅ Runs comfortably |
| LFM2.5-1.2B-Instruct-BF16.gguf | GGUF | 2.3 GB | 3.3 GB | ✅ Runs comfortably |
| model.safetensors | fp16 | 4.7 GB | 5.8 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 125K ctx | 4.7 GB | 8.5 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run lfm2-5-1-2b-instruct-gguf # pin the quantization explicitly $ ollama run lfm2-5-1-2b-instruct-gguf-q4_0
$ huggingface-cli download LiquidAI/LFM2.5-1.2B-Instruct-GGUF-GGUF \
LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf --local-dir .
$ llama-cli -m LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/lfm2-5-1-2b-instruct-gguf
{
"hf_id": "LiquidAI/LFM2.5-1.2B-Instruct-GGUF",
"params_b": 1.20,
"context_length": 128000,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 257487,
"vram_estimates": [
{ "quant": "GGUF", "gb": 3.3 },
{ "quant": "Q4_0", "gb": 1.4 }
],
"updated_at": "2026-09-23T01:00:32Z"
}
Specifications
- Parameters
- 1.2 B
- Context length
- 128,000
- Licence
- other
- First seen on the Hub
- 2026-01-04
- Base model
- LFM2.5-1.2B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model