π Model Description
base_model: TeichAI/Qwen3-32B-Kimi-K2-Thinking-Distill tags:
- llama.cpp
- gguf
- unsloth
- en
- TeichAI/kimi-k2-thinking-1000x
Qwen3 32B - Kimi K2 Thinking Distill
This model was trained on 1000 high reasoning examples from Kimi-K2-Thinking.
- 𧬠Datasets:
TeichAI/kimi-k2-thinking-1000x
- π Base Model:
unsloth/Qwen3-32B
- ⚡ Use cases:
π GGUF File List
| π Filename | π¦ Size | β‘ Download |
|---|---|---|
|
Qwen3-32B-Kimi-K2-Thinking-Distill.bf16.gguf
LFS
FP16
|
61.03 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.f16.gguf
LFS
FP16
|
61.03 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.iq2_m.gguf
LFS
Q2
|
10.58 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.iq2_xs.gguf
LFS
Q2
|
9.27 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.iq3_m.gguf
LFS
Q3
|
13.9 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.iq3_xs.gguf
LFS
Q3
|
12.76 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.iq4_nl.gguf
LFS
Q4
|
17.4 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.iq4_xs.gguf
LFS
Q4
|
16.48 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.q3_k_m.gguf
LFS
Q3
|
14.87 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.q3_k_s.gguf
LFS
Q3
|
13.4 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.q4_k_m.gguf
Recommended
LFS
Q4
|
18.4 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.q5_k_m.gguf
LFS
Q5
|
21.62 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.q6_k.gguf
LFS
Q6
|
25.04 GB | Download |
|
Qwen3-32B-Kimi-K2-Thinking-Distill.q8_0.gguf
LFS
Q8
|
32.43 GB | Download |