LFM2.5-24B-A2B-GGUF
Unsloth Dynamic 3.0 achieves superior accuracy & outperforms other leading quants.
Params
24.0 B
Context
131,072
Downloads 30d
430 K
Likes
121
Download history
daily snapshots · 13 days430 K147 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-UD-IQ2_XXS.gguf | IQ2_XXS | 7.5 GB | 12.3 GB | ✅ Runs comfortably |
| LFM2.5-24B-A2B-UD-IQ2_M.gguf | IQ2_M | 7.5 GB | 12.4 GB | ✅ Runs comfortably |
| LFM2.5-24B-A2B-UD-Q2_K_XL.gguf | Q2_K_XL | 8.0 GB | 12.9 GB | ✅ Runs comfortably |
| LFM2.5-24B-A2B-UD-IQ3_XXS.gguf | IQ3_XXS | 9.0 GB | 14.0 GB | ✅ Runs comfortably |
| LFM2.5-24B-A2B-UD-Q3_K_XL.gguf | Q3_K_XL | 10.9 GB | 16.1 GB | ✅ Runs comfortably |
| LFM2.5-24B-A2B-UD-Q4_K_XL.gguf | Q4_K_XL | 14.9 GB | 20.5 GB | ⚠️ Tight — reduce context |
| LFM2.5-24B-A2B-Q8_0.gguf | Q8_0 | 25.5 GB | 32.1 GB | ❌ Won’t fit |
| LFM2.5-24B-A2B-BF16.gguf | GGUF | 48.0 GB | 56.9 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-gguf-unsloth # pin the quantization explicitly $ ollama run lfm2-5-24b-a2b-gguf-unsloth-q4_k_xl
$ huggingface-cli download unsloth/LFM2.5-24B-A2B-GGUF-GGUF \
LFM2.5-24B-A2B-UD-Q4_K_XL.gguf --local-dir .
$ llama-cli -m LFM2.5-24B-A2B-UD-Q4_K_XL.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/lfm2-5-24b-a2b-gguf-unsloth
{
"hf_id": "unsloth/LFM2.5-24B-A2B-GGUF",
"params_b": 24.00,
"context_length": 131072,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 429548,
"vram_estimates": [
{ "quant": "GGUF", "gb": 56.9 },
{ "quant": "Q8_0", "gb": 32.1 }
],
"updated_at": "2026-10-29T01:00:26Z"
}
Specifications
- Parameters
- 24.0 B
- Context length
- 131,072
- Licence
- other
- First seen on the Hub
- 2026-10-13
- 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