Barney Greenway

McG-221

·

AI & ML interests

LLMs on Apple Silicon

Recent Activity

liked a model about 5 hours ago

Naphula/Goetia-26B-A4B-v1.4

liked a model about 5 hours ago

mudler/Qwopus3.6-35B-A3B-Coder-APEX-MTP-GGUF

liked a model about 6 hours ago

dnotitia/DNA3.0-35B-A3B

View all activity

Organizations

upvoted a collection 4 days ago

Ornith-1.0

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated 6 days ago • 289

upvoted a collection 5 days ago

Ornith 1.0

MLX versions of Ornith 1.0 • 6 items • Updated 6 days ago • 4

upvoted a collection 24 days ago

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 18 days ago • 98

upvoted a collection 27 days ago

Qwen 3.x MTP

MLX MTP drafter checkpoints for Qwen 3.x speculative decoding with mlx-vlm. • 12 items • Updated Jun 1 • 9

upvoted 2 collections 28 days ago

Gemma 4 QAT Q4_0

19 items • Updated 28 days ago • 139

Gemma 4 QAT

40 items • Updated 28 days ago • 13

upvoted 4 collections about 2 months ago

Gemma-4-31B-IT-unsloth-mlx

Gemma-4-31B-IT (dense vision-language) quantized for Apple Silicon (MLX) — Unsloth Dynamic 2.0 with AWQ imatrix pre-scaling. • 9 items • Updated May 16 • 1

Gemma-4-26B-IT-unsloth-mlx

Gemma-4-26B-A4B-IT MoE quantized for Apple Silicon (MLX) — Unsloth Dynamic 2.0 with AWQ imatrix pre-scaling. • 8 items • Updated May 16 • 1

Magistry

Q1 2026 merges based on Mistral 24B • 2 items • Updated Mar 22 • 2

Qwen-3.6-unsloth-mlx

AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 18 items • Updated May 15 • 19

upvoted 3 collections 2 months ago

gemma-4-abliterated

19 items • Updated 12 days ago • 30

Uncensored Gemma 4 MLX

10 items • Updated Apr 16 • 2

Qwen3.6

4 items • Updated Apr 22 • 425

upvoted 6 collections 3 months ago

Qwen3.5

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 18 days ago • 161

Qwen3.5-122B-A10B

MINT quantized versions of Qwen3.5-122B-A10B at multiple budget targets (MLX & GGUF) • 4 items • Updated Apr 7 • 2

APEX Quants (GGUF)

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 39 items • Updated 1 day ago • 124

Gemma 4

88 items • Updated 30 days ago • 146

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 36 items • Updated 18 days ago • 227

Qwen-3.5-unsloth-mlx

AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 20 items • Updated Mar 29 • 20

upvoted a collection 4 months ago

Qwen3.5-9B Heretic MLX

8 items • Updated Apr 15 • 7