Downloads · 30 days
51
3% of all-time downloads
mamba-370m-hf-turkish-GGUF
coder423/mamba-370m-hf-turkish-GGUF
mamba-370m-hf-turkish-GGUF is a text generation model from coder423. Use it when you need the model to write or continue text. It is set up for gguf.
GGUF quantized versions of serda-dev/mamba-370m-hf-turkish.
All-time downloads
1.5K
Public
Repo size
2.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- Access
- Public
- Created
- Feb 22, 2026
- Updated
- Feb 22, 2026
- SHA
- 98e2fbba
Base models
Model card
From the Hugging Face model README
Mamba-370m Turkish - GGUF
GGUF quantized versions of serda-dev/mamba-370m-hf-turkish.
Available Quantizations
| File | Quant Type | Size |
|---|---|---|
| mamba-370m-hf-turkish-f16.gguf | F16 | 714.7 MB |
| mamba-370m-hf-turkish-q2-k.gguf | Q2_K | 151.6 MB |
| mamba-370m-hf-turkish-q3-k-m.gguf | Q3_K_M | 181.8 MB |
| mamba-370m-hf-turkish-q4-k-m.gguf | Q4_K_M | 222.0 MB |
| mamba-370m-hf-turkish-q5-k-m.gguf | Q5_K_M | 259.5 MB |
| mamba-370m-hf-turkish-q6-k.gguf | Q6_K | 300.8 MB |
| mamba-370m-hf-turkish-q8-0.gguf | Q8_0 | 384.6 MB |
Usage
These GGUF files can be used with llama.cpp and compatible tools that support Mamba architecture.
./llama-cli -m mamba-370m-hf-turkish-q4-k-m.gguf -p "Turkiye'nin baskenti" -n 128
Source Model
- Original model: serda-dev/mamba-370m-hf-turkish
- Architecture: Mamba (Selective State Space Model)
- Language: Turkish
- Parameters: 370M
Conversion Details
- Converted using
llama.cppconvert_hf_to_gguf.py - Base format: F16
- Quantized variants: Q2_K, Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0
- Task
- Text Generation
- Library
- gguf
- Languages
- tr
- Created
- Feb 22, 2026
- Updated
- Feb 22, 2026