LFM2-24B-A2B-MLX-4bit
👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.
Params
23.8 B
Context
128,000
Downloads 30d
151 K
Likes
4
Download history
daily snapshots · 7 days151 K139 K
Nov 4Nov 6Nov 8Nov 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 |
|---|---|---|---|---|
| model.safetensors | u32 | 13.4 GB | 18.8 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 125K ctx | 13.4 GB | 71.1 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$ curl -s https://aimodelscomparison.com/api/v1/models/lfm2-24b-a2b-mlx-4bit
{
"hf_id": "lmstudio-community/LFM2-24B-A2B-MLX-4bit",
"params_b": 23.84,
"context_length": 128000,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 151169,
"vram_estimates": [
{ "quant": "u32", "gb": 18.8 }
],
"updated_at": "2026-11-04T01:00:21Z"
}
Specifications
- Architecture
- Lfm2MoeForCausalLM
- Parameters
- 23.8 B
- Tensor type
- U32
- Context length
- 128,000
- Vocabulary
- 65,536
- Layers / heads
- 40 / 32
- Licence
- other
- First seen on the Hub
- 2026-02-23
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-04
Compare with any text-generation model