Downloads · 30 days
348
22% of all-time downloads
kirilldual0987/MIXdevAI-qwen-GGUF
MIXdevAI-qwen-GGUF is a text generation model from kirilldual0987. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Full set of GGUF quantizations for Kolyadual/MIXdevAI-qwen.
Downloads · 30 days
348
22% of all-time downloads
All-time downloads
1.6K
Public
Repo size
44.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf44.9 GB · 100%
From the Hugging Face model README
Full set of GGUF quantizations for Kolyadual/MIXdevAI-qwen.
Based on the Qwen3 architecture (Qwen3ForCausalLM) with 36 layers, 262K context length, and 2560 embedding dimension.
| File | Quantization | Type |
|---|---|---|
mixdev-qwen-f16.gguf | F16 | Base Model |
mixdev-qwen-q8_0.gguf | Q8_0 | Text Model |
mixdev-qwen-q6_k.gguf | Q6_K | Text Model |
mixdev-qwen-q5_k_m.gguf | Q5_K_M | Text Model |
mixdev-qwen-q5_k_s.gguf | Q5_K_S | Text Model |
mixdev-qwen-q5_1.gguf | Q5_1 | Text Model |
mixdev-qwen-q5_0.gguf | Q5_0 | Text Model |
mixdev-qwen-q4_k_m.gguf | Q4_K_M | Text Model |
mixdev-qwen-q4_k_s.gguf | Q4_K_S | Text Model |
mixdev-qwen-q4_1.gguf | Q4_1 | Text Model |
mixdev-qwen-q4_0.gguf | Q4_0 | Text Model |
mixdev-qwen-q3_k_l.gguf | Q3_K_L | Text Model |
mixdev-qwen-q3_k_m.gguf | Q3_K_M | Text Model |
mixdev-qwen-q3_k_s.gguf | Q3_K_S | Text Model |
mixdev-qwen-q2_k.gguf | Q2_K | Text Model |
Example using llama.cpp server:
llama-server \
-m mixdev-qwen-q4_k_m.gguf \
-ngl 999 \
--host 0.0.0.0 --port 8080 \
-c 32768