48 lines
2.0 KiB
Markdown
48 lines
2.0 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
base_model:
|
|
- Qwen/Qwen3-1.7B
|
|
pipeline_tag: text-generation
|
|
library_name: transformers
|
|
tags:
|
|
- text-generation-inference
|
|
---
|
|
|
|
# **Mintaka-Qwen3-1.6B-V3.1-GGUF**
|
|
|
|
> Mintaka-Qwen3-1.6B-V3.1 is a high-efficiency, science-focused reasoning model based on Qwen-1.6B and trained on DeepSeek v3.1 synthetic traces (10,000 entries). It is optimized for random event simulation, logical-problem analysis, and structured scientific reasoning. The model balances symbolic precision with lightweight deployment, making it suitable for researchers, educators, and developers seeking efficient reasoning under constrained compute.
|
|
|
|
## Model Files
|
|
|
|
| File Name | Quant Type | File Size |
|
|
| - | - | - |
|
|
| Mintaka-Qwen3-1.6B-V3.1.BF16.gguf | BF16 | 3.45 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.F16.gguf | F16 | 3.45 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.F32.gguf | F32 | 6.89 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q2_K.gguf | Q2_K | 778 MB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q3_K_L.gguf | Q3_K_L | 1 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q3_K_M.gguf | Q3_K_M | 940 MB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q3_K_S.gguf | Q3_K_S | 867 MB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q4_0.gguf | Q4_0 | 1.05 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q4_1.gguf | Q4_1 | 1.14 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q4_K.gguf | Q4_K | 1.11 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q4_K_M.gguf | Q4_K_M | 1.11 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q4_K_S.gguf | Q4_K_S | 1.06 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q5_0.gguf | Q5_0 | 1.23 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q5_1.gguf | Q5_1 | 1.32 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q5_K.gguf | Q5_K | 1.26 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q5_K_M.gguf | Q5_K_M | 1.26 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q5_K_S.gguf | Q5_K_S | 1.23 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q6_K.gguf | Q6_K | 1.42 GB |
|
|
| Mintaka-Qwen3-1.6B-V3.1.Q8_0.gguf | Q8_0 | 1.83 GB |
|
|
|
|
## Quants Usage
|
|
|
|
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
|
|
|
|
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
types (lower is better):
|
|
|
|
 |