Model Intelligence Sheet
mamelles/LFM2.5-350M-Wolof-CPT-v3-GGUF overview
LFM2.5 350M Wolof CPT v3 GGUF Private production artifact ongoing/experimental . Exact base: Tonic/LFM2.5 350M Wolof CPT v3 Training stage: CPT + GGUF export T…
Runs locally from ~211.5 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
6 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| LFM2.5-350M-Wolof-CPT-v3-BF16.gguf | GGUF | BF16 | 684.2 MB | Download |
| LFM2.5-350M-Wolof-CPT-v3-Q4_0.gguf | GGUF | Q4_0 | 211.5 MB | Download |
| LFM2.5-350M-Wolof-CPT-v3-Q4_K_M.gguf | GGUF | Q4_K_M | 221.0 MB | Download |
| LFM2.5-350M-Wolof-CPT-v3-Q5_K_M.gguf | GGUF | Q5_K_M | 250.7 MB | Download |
| LFM2.5-350M-Wolof-CPT-v3-Q6_K.gguf | GGUF | Q6_K | 282.1 MB | Download |
| LFM2.5-350M-Wolof-CPT-v3-Q8_0.gguf | GGUF | Q8_0 | 364.7 MB | Download |
Model Details
| Model ID | mamelles/LFM2.5-350M-Wolof-CPT-v3-GGUF |
|---|---|
| Author | mamelles |
| Pipeline | text-generation |
| License | — |
| Base model | Tonic/LFM2.5-350M-Wolof-CPT-v3 |
| Last modified | 2026-10-07T17:13:03.000Z |
Model README
---
library_name: gguf
pipeline_tag: text-generation
tags:
- gguf
- llama.cpp
- wolof
- lfm2.5
- private-production-artifact
base_model: Tonic/LFM2.5-350M-Wolof-CPT-v3
---
LFM2.5-350M-Wolof-CPT-v3-GGUF
Private production artifact (ongoing/experimental).
- Exact base:
Tonic/LFM2.5-350M-Wolof-CPT-v3 - Training stage:
CPT(+ GGUF export) - Tokenizer family: see base model card
- Data caveat: Wolof CPT/SFT mixture; no public leakage claims
- Limitations: experimental; verify generation quality before downstream use
- Private production artifact for gated llama.cpp deployment
Files
GGUF quant matrix following LiquidAI parity: BF16, F16, Q8_0, Q6_K, Q5_K_M, Q4_K_M, Q4_0.
Run
llama-cli -hf <namespace>/LFM2.5-350M-Wolof-CPT-v3-GGUF:Q4_K_M -p "Salaam aleekum"Run mamelles/LFM2.5-350M-Wolof-CPT-v3-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models