TwIL-LM3
A 3B reasoning model for formal logic tasks, built from HuggingFaceTB/SmolLM3-3B through LoRA supervised fine-tuning, checkpoint fusion, WiSE-FT weight interpolation, and entropy-weighted GRPO reinforcement learning.
Params
3.1 B
Context
65,536
Downloads 30d
384 K
Likes
90
Download history
daily snapshots · 25 days408 K179 K
Aug 28Sep 5Sep 13Sep 21
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 |
|---|---|---|---|---|
| TwIL-LM3-Q4_K_M.gguf | Q4_K_M | 1.9 GB | 3.1 GB | ✅ Runs comfortably |
| TwIL-LM3-Q5_K_M.gguf | Q5_K_M | 2.2 GB | 3.4 GB | ✅ Runs comfortably |
| TwIL-LM3-Q6_K.gguf | Q6_K | 2.5 GB | 3.7 GB | ✅ Runs comfortably |
| TwIL-LM3-Q8_0.gguf | Q8_0 | 3.3 GB | 4.6 GB | ✅ Runs comfortably |
| TwIL-LM3-F16.gguf | GGUF | 6.2 GB | 7.7 GB | ✅ Runs comfortably |
| model.safetensors | bf16 | 6.2 GB | 7.7 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 64K ctx | 6.2 GB | 11.0 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 twil-lm3 # pin the quantization explicitly $ ollama run twil-lm3-q4_k_m
$ huggingface-cli download webAI-Official/TwIL-LM3-GGUF \
TwIL-LM3-Q4_K_M.gguf --local-dir .
$ llama-cli -m TwIL-LM3-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/twil-lm3
{
"hf_id": "webAI-Official/TwIL-LM3",
"params_b": 3.08,
"context_length": 65536,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 383511,
"vram_estimates": [
{ "quant": "GGUF", "gb": 7.7 },
{ "quant": "Q4_K_M", "gb": 3.1 }
],
"updated_at": "2026-09-10T01:00:14Z"
}
Specifications
- Architecture
- SmolLM3ForCausalLM
- Parameters
- 3.1 B
- Tensor type
- BF16
- Context length
- 65,536
- Vocabulary
- 128,256
- Layers / heads
- 36 / 16
- Licence
- other
- First seen on the Hub
- 2026-08-03
- Base model
- SmolLM3-3B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model