LFM2.5-24B-A2B-Uncensored-GGUF
Liquid's refusal behaviour projected out of the original weights, in the second two thirds of the network only. Shipped two ways: six baked GGUF builds, and a 24 MB LoRA adapter for the LFM2.5-24B-A2B quants you already have. The measurements behind this card are public. Built by the team behind Atomic Chat, the app that runs open-weight models locally and offline. On held-out prompts, refusals fall from 96.3% to 1.2...
Params
24.0 B
Context
131,072
Downloads 30d
639 K
Likes
77
Download history
daily snapshots · 13 days639 K151 K
Oct 29Nov 2Nov 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 |
|---|---|---|---|---|
| LFM2.5-24B-A2B-Uncensored-LoRA.gguf | GGUF | 0.0 GB | 4.1 GB | ✅ Runs comfortably |
| LFM2.5-24B-A2B-Uncensored-AD-IQ3_M.gguf | IQ3_M | 12.1 GB | 17.4 GB | ✅ Runs comfortably |
| LFM2.5-24B-A2B-Uncensored-AD-IQ4_XS.gguf | IQ4_XS | 14.5 GB | 20.0 GB | ⚠️ Tight — reduce context |
| LFM2.5-24B-A2B-Uncensored-AD-Q4_K_M.gguf | Q4_K_M | 15.4 GB | 21.0 GB | ⚠️ Tight — reduce context |
| LFM2.5-24B-A2B-Uncensored-AD-Q5_K_M.gguf | Q5_K_M | 17.3 GB | 23.1 GB | ⚠️ Tight — reduce context |
| LFM2.5-24B-A2B-Uncensored-AD-Q6_K.gguf | Q6_K | 20.9 GB | 27.1 GB | ❌ Won’t fit |
| LFM2.5-24B-A2B-Uncensored-AD-Q8_0.gguf | Q8_0 | 25.7 GB | 32.4 GB | ❌ Won’t fit |
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 lfm2-5-24b-a2b-uncensored-gguf # pin the quantization explicitly $ ollama run lfm2-5-24b-a2b-uncensored-gguf-q4_k_m
$ huggingface-cli download AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF-GGUF \
LFM2.5-24B-A2B-Uncensored-AD-Q4_K_M.gguf --local-dir .
$ llama-cli -m LFM2.5-24B-A2B-Uncensored-AD-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/lfm2-5-24b-a2b-uncensored-gguf
{
"hf_id": "AtomicChat/LFM2.5-24B-A2B-Uncensored-GGUF",
"params_b": 24.00,
"context_length": 131072,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 639217,
"vram_estimates": [
{ "quant": "IQ3_M", "gb": 17.4 },
{ "quant": "IQ4_XS", "gb": 20.0 }
],
"updated_at": "2026-10-29T01:00:20Z"
}
Specifications
- Parameters
- 24.0 B
- Context length
- 131,072
- Licence
- other
- First seen on the Hub
- 2026-10-09
- Base model
- LFM2.5-24B-A2B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-29
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model
Popular comparisons
Appears in