MLX Quantisations for Qwen 3.8 2B
🏗️ Building on HF
Siddh Jagani
SiddhJagani
AI & ML interests
Building local AI systems, LLM tools, RAG infrastructure, and MLX model deployments.
Recent Activity
liked a model 1 day ago
prithivMLmods/chandra-ocr-2-GGUF liked a model 3 days ago
ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF updated a Space about 1 month ago
SiddhJagani/StatsOrganizations
MLX Quantisations for Qwen 3.8 9B
MLX Claude Opus 4.5
-
SiddhJagani/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q8
Text Generation • 15B • Updated • 15 -
SiddhJagani/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q6
Text Generation • 15B • Updated • 24 -
SiddhJagani/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q3
Text Generation • 15B • Updated • 12 -
SiddhJagani/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q2
Text Generation • 15B • Updated • 16
MLX Non-Thinking Models
-
SiddhJagani/gpt-oss-20b-no-think-mlx-2Bit
Text Generation • 21B • Updated • 188 • 2 -
SiddhJagani/gpt-oss-20b-no-think-mlx-Q3
Text Generation • 21B • Updated • 53 -
SiddhJagani/gpt-oss-20b-no-think-mlx-Q4
Text Generation • 21B • Updated • 31 -
SiddhJagani/gpt-oss-20b-no-think-mlx-Q6
Text Generation • 21B • Updated • 34
MLX Quantisations for Qwen 3.8 4B
MLX 8B Claude Opus 4.5
-
SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q8
Text Generation • 8B • Updated • 23 -
SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q6
Text Generation • 8B • Updated • 23 -
SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q4
Text Generation • 8B • Updated • 21
MLX Based GPT-OSS-Safeguard models
-
SiddhJagani/gpt-oss-safeguard-20b-mlx-Q2
Text Generation • 21B • Updated • 52 -
SiddhJagani/gpt-oss-safeguard-20b-mlx-Q3
Text Generation • 21B • Updated • 36 -
SiddhJagani/gpt-oss-safeguard-20b-mlx-Q4
Text Generation • 21B • Updated • 32 -
SiddhJagani/gpt-oss-safeguard-20b-mlx-Q6
Text Generation • 21B • Updated • 48
MLX Quantisations for Qwen 3.8 2B
MLX Quantisations for Qwen 3.8 4B
MLX Quantisations for Qwen 3.8 9B
MLX 8B Claude Opus 4.5
-
SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q8
Text Generation • 8B • Updated • 23 -
SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q6
Text Generation • 8B • Updated • 23 -
SiddhJagani/Nemotron-Cascade-8B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q4
Text Generation • 8B • Updated • 21
MLX Claude Opus 4.5
-
SiddhJagani/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q8
Text Generation • 15B • Updated • 15 -
SiddhJagani/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q6
Text Generation • 15B • Updated • 24 -
SiddhJagani/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q3
Text Generation • 15B • Updated • 12 -
SiddhJagani/Nemotron-Cascade-14B-Thinking-Claude-4.5-Opus-High-Reasoning-Distill-mlx-Q2
Text Generation • 15B • Updated • 16
MLX Based GPT-OSS-Safeguard models
-
SiddhJagani/gpt-oss-safeguard-20b-mlx-Q2
Text Generation • 21B • Updated • 52 -
SiddhJagani/gpt-oss-safeguard-20b-mlx-Q3
Text Generation • 21B • Updated • 36 -
SiddhJagani/gpt-oss-safeguard-20b-mlx-Q4
Text Generation • 21B • Updated • 32 -
SiddhJagani/gpt-oss-safeguard-20b-mlx-Q6
Text Generation • 21B • Updated • 48
MLX Non-Thinking Models
-
SiddhJagani/gpt-oss-20b-no-think-mlx-2Bit
Text Generation • 21B • Updated • 188 • 2 -
SiddhJagani/gpt-oss-20b-no-think-mlx-Q3
Text Generation • 21B • Updated • 53 -
SiddhJagani/gpt-oss-20b-no-think-mlx-Q4
Text Generation • 21B • Updated • 31 -
SiddhJagani/gpt-oss-20b-no-think-mlx-Q6
Text Generation • 21B • Updated • 34