Liem Vo-Nguyen PRO

lvonguyen

webbrain-one-308526's profile picture

webbrain-6f3q2's profile picture

Overseer667's profile picture

https://www.linkedin.com/in/liemvonguyen/

robertflay69
lvonguyen
liemvonguyen

AI & ML interests

None yet

Recent Activity

updated a collection 13 days ago

dgx-spark-x2

updated a collection 29 days ago

dgx-spark-x2

updated a collection about 2 months ago

h200x4

View all activity

Organizations

lvonguyen 's collections 12

h200x4

Four-H200 model candidates. Notes distinguish published configurations from verified capacity; weight size excludes KV cache and runtime memory.

dealignai/GLM-5.3-Flash-CYBERSECURITY-W4A16

Text Generation • 321B • Updated Sep 19 • 5.5k • 46
deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated 16 days ago • 2.13M • • 4.83k
dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Image-Text-to-Text • 763B • Updated Sep 11 • 37.6k • 814
dealignai/GLM-5.3-Flash-UNCENSORED-FP8

321B • Updated Sep 19 • 17.3k • 180

private-cloud

Self-hosted model research. Use hardware-specific collections for placement and verify runtime compatibility and measured memory.

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

Image-Text-to-Text • 305B • Updated Sep 1 • 216k • • 962
Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated Aug 27 • 4.03M • • 6.69k
unsloth/GLM-5.3-Flash-GGUF

Text Generation • 321B • Updated 27 days ago • 830k • 513
unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF

284B • Updated Sep 9 • 7.42k • 100

deepseek-v4-flash-0731

DeepSeek-V4-Flash-0731 community variants. Compare revisions, formats, capability preservation and serving requirements.

huihui-ai/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF

Text Generation • 284B • Updated Aug 3 • 372k • 235
apetersson/DeepSeek-V4-Flash-0731-Abliterated-FP8

Text Generation • 304B • Updated Aug 1 • 1.1k • 38
apetersson/DeepSeek-V4-Flash-0731-Abliterated-DS4-Quality128

Text Generation • 284B • Updated Aug 4 • 610 • 7
squanchyzx/DeepSeek-V4-Flash-0731-HERETIC-Abliterated-FP8

Text Generation • 305B • Updated Aug 12 • 388 • 21

mini

Small local model candidates for lightweight tasks and runtime experiments.

mlx-community/Qwen2.5-1.5B-Instruct-bf16

Text Generation • 2B • Updated Sep 18, 2024 • 233

heretic-mlx-med

Medium-memory MLX model candidates. Quantization and actual memory requirements vary by checkpoint.

nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-Text-mxfp4-mlx

Text Generation • 27B • Updated Apr 29 • 32
mlx-community/gemma-4-31B-it-uncensored-heretic-4bit

Image-Text-to-Text • 31B • Updated May 19 • 1.55k • 6
nightmedia/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking-qx86-hi-mlx

Image-Text-to-Text • 9B • Updated Mar 18 • 576 • 8

inference-all

General model research inventory. Use hardware and format collections for placement, with matched evaluations for selected candidates.

WhiteRabbitNeo/WhiteRabbitNeo-33B-v1.5

Text Generation • 33B • Updated Feb 15, 2024 • 231 • 82
GGUF-A-Lot/DeepHat-V1-7B-GGUF

8B • Updated Sep 15, 2025 • 559 • 5
DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking

Image-Text-to-Text • 31B • Updated Jun 23 • 679 • • 97
Stabhappy/gemma-4-31B-it-heretic-Gguf

31B • Updated Apr 4 • 2.14k • 16

dgx-spark-x2

Two-DGX-Spark (GB10) candidates. Each host has separate memory; ARM64/SM121 compatibility and full-context capacity require validation.

dealignai/Qwen3.8-Flash-Next-CYBERSECURITY-NVFP4

Image-Text-to-Text • 120B • Updated Sep 4 • 7.73k • 44
nvidia/Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 120B • Updated Sep 5 • 316k • 426
nvidia/DeepSeek-V4-Flash-0731-NVFP4

Text Generation • 304B • Updated Sep 2 • 3.85k • 57
dealignai/GLM-5.3-Flash-CYBERSECURITY-W4A16

Text Generation • 321B • Updated Sep 19 • 5.5k • 46

dell-trial-rtx6000pro-8x

Eight-GPU RTX PRO 6000 trial candidates. Verify board generation, memory, interconnect and runtime; membership is not an allocation.

deepseek-ai/DeepSeek-V4-Pro-0813

Text Generation • 1.7T • Updated Aug 13 • 152k • • 909
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

Image-Text-to-Text • 305B • Updated Sep 1 • 216k • • 962

embedding

Embedding candidates for semantic retrieval. Compare vector dimensions, retrieval quality and runtime support.

jedisct1/Qwen3-Embedding-8B-mlx

Text Generation • 8B • Updated Jan 10 • 846 • 2
Aqua00/Nemotron-3-Embed-8B-GGUF

Sentence Similarity • 8B • Updated Jul 21 • 1.95k

inference-heretic

Uncensored and Heretic-derived inference candidates. Evaluate capability and reliability separately from refusal-rate claims.

llmfan46/Qwen3.6-35B-A3B-uncensored-heretic

Image-Text-to-Text • 35B • Updated May 7 • 1.6k • 97
llmfan46/gemma-4-31B-it-uncensored-heretic

Image-Text-to-Text • 31B • Updated Sep 19 • 2.23k • • 165
llmfan46/gpt-oss-120b-heretic-v2

Text Generation • 117B • Updated Mar 27 • 142 • 2
llmfan46/Qwen3.6-27B-uncensored-heretic-v2

Image-Text-to-Text • 27B • Updated May 28 • 130 • • 40

heretic-mlx-lrg

Larger local and MLX model candidates. Check weight, cache and runtime memory before choosing hardware.

nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-mxfp8-mlx

Image-Text-to-Text • 27B • Updated Apr 29 • 26 • 3
nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-Text-mxfp4-mlx

Text Generation • 27B • Updated Apr 29 • 32
nightmedia/Qwen3.6-27B-Polaris-Heretic-mxfp8-mlx

Image-Text-to-Text • 27B • Updated Apr 30 • 14
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-8bit

Image-Text-to-Text • 27B • Updated May 6 • 161 • 2

heretic

Heretic and other weight-edited candidates. Track revisions, quantization, capability preservation and limitations.

mradermacher/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-GGUF

12B • Updated Jan 10 • 15.9k • 72
Stabhappy/gemma-4-31B-it-heretic-Gguf

31B • Updated Apr 4 • 2.14k • 16
coder3101/gemma-4-31B-it-heretic

Image-Text-to-Text • 31B • Updated Apr 14 • 2.06k • • 97
Youssofal/MiniMax-M2.7-Abliterated-Heretic-GGUF

Text Generation • 229B • Updated Apr 14 • 2.94k • 48

h200x4

Four-H200 model candidates. Notes distinguish published configurations from verified capacity; weight size excludes KV cache and runtime memory.

dealignai/GLM-5.3-Flash-CYBERSECURITY-W4A16

Text Generation • 321B • Updated Sep 19 • 5.5k • 46
deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated 16 days ago • 2.13M • • 4.83k
dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Image-Text-to-Text • 763B • Updated Sep 11 • 37.6k • 814
dealignai/GLM-5.3-Flash-UNCENSORED-FP8

321B • Updated Sep 19 • 17.3k • 180

dgx-spark-x2

Two-DGX-Spark (GB10) candidates. Each host has separate memory; ARM64/SM121 compatibility and full-context capacity require validation.

dealignai/Qwen3.8-Flash-Next-CYBERSECURITY-NVFP4

Image-Text-to-Text • 120B • Updated Sep 4 • 7.73k • 44
nvidia/Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 120B • Updated Sep 5 • 316k • 426
nvidia/DeepSeek-V4-Flash-0731-NVFP4

Text Generation • 304B • Updated Sep 2 • 3.85k • 57
dealignai/GLM-5.3-Flash-CYBERSECURITY-W4A16

Text Generation • 321B • Updated Sep 19 • 5.5k • 46

private-cloud

Self-hosted model research. Use hardware-specific collections for placement and verify runtime compatibility and measured memory.

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

Image-Text-to-Text • 305B • Updated Sep 1 • 216k • • 962
Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated Aug 27 • 4.03M • • 6.69k
unsloth/GLM-5.3-Flash-GGUF

Text Generation • 321B • Updated 27 days ago • 830k • 513
unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF

284B • Updated Sep 9 • 7.42k • 100

dell-trial-rtx6000pro-8x

Eight-GPU RTX PRO 6000 trial candidates. Verify board generation, memory, interconnect and runtime; membership is not an allocation.

deepseek-ai/DeepSeek-V4-Pro-0813

Text Generation • 1.7T • Updated Aug 13 • 152k • • 909
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp

Image-Text-to-Text • 305B • Updated Sep 1 • 216k • • 962

deepseek-v4-flash-0731

DeepSeek-V4-Flash-0731 community variants. Compare revisions, formats, capability preservation and serving requirements.

huihui-ai/Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF

Text Generation • 284B • Updated Aug 3 • 372k • 235
apetersson/DeepSeek-V4-Flash-0731-Abliterated-FP8

Text Generation • 304B • Updated Aug 1 • 1.1k • 38
apetersson/DeepSeek-V4-Flash-0731-Abliterated-DS4-Quality128

Text Generation • 284B • Updated Aug 4 • 610 • 7
squanchyzx/DeepSeek-V4-Flash-0731-HERETIC-Abliterated-FP8

Text Generation • 305B • Updated Aug 12 • 388 • 21

embedding

Embedding candidates for semantic retrieval. Compare vector dimensions, retrieval quality and runtime support.

jedisct1/Qwen3-Embedding-8B-mlx

Text Generation • 8B • Updated Jan 10 • 846 • 2
Aqua00/Nemotron-3-Embed-8B-GGUF

Sentence Similarity • 8B • Updated Jul 21 • 1.95k

mini

Small local model candidates for lightweight tasks and runtime experiments.

mlx-community/Qwen2.5-1.5B-Instruct-bf16

Text Generation • 2B • Updated Sep 18, 2024 • 233

inference-heretic

Uncensored and Heretic-derived inference candidates. Evaluate capability and reliability separately from refusal-rate claims.

llmfan46/Qwen3.6-35B-A3B-uncensored-heretic

Image-Text-to-Text • 35B • Updated May 7 • 1.6k • 97
llmfan46/gemma-4-31B-it-uncensored-heretic

Image-Text-to-Text • 31B • Updated Sep 19 • 2.23k • • 165
llmfan46/gpt-oss-120b-heretic-v2

Text Generation • 117B • Updated Mar 27 • 142 • 2
llmfan46/Qwen3.6-27B-uncensored-heretic-v2

Image-Text-to-Text • 27B • Updated May 28 • 130 • • 40

heretic-mlx-med

Medium-memory MLX model candidates. Quantization and actual memory requirements vary by checkpoint.

nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-Text-mxfp4-mlx

Text Generation • 27B • Updated Apr 29 • 32
mlx-community/gemma-4-31B-it-uncensored-heretic-4bit

Image-Text-to-Text • 31B • Updated May 19 • 1.55k • 6
nightmedia/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking-qx86-hi-mlx

Image-Text-to-Text • 9B • Updated Mar 18 • 576 • 8

heretic-mlx-lrg

Larger local and MLX model candidates. Check weight, cache and runtime memory before choosing hardware.

nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-mxfp8-mlx

Image-Text-to-Text • 27B • Updated Apr 29 • 26 • 3
nightmedia/Qwen3.6-27B-Architect-DS9-Polaris-Heretic-Text-mxfp4-mlx

Text Generation • 27B • Updated Apr 29 • 32
nightmedia/Qwen3.6-27B-Polaris-Heretic-mxfp8-mlx

Image-Text-to-Text • 27B • Updated Apr 30 • 14
froggeric/Qwen3.6-27B-Uncensored-Heretic-v2-MLX-8bit

Image-Text-to-Text • 27B • Updated May 6 • 161 • 2

inference-all

General model research inventory. Use hardware and format collections for placement, with matched evaluations for selected candidates.

WhiteRabbitNeo/WhiteRabbitNeo-33B-v1.5

Text Generation • 33B • Updated Feb 15, 2024 • 231 • 82
GGUF-A-Lot/DeepHat-V1-7B-GGUF

8B • Updated Sep 15, 2025 • 559 • 5
DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking

Image-Text-to-Text • 31B • Updated Jun 23 • 679 • • 97
Stabhappy/gemma-4-31B-it-heretic-Gguf

31B • Updated Apr 4 • 2.14k • 16

heretic

Heretic and other weight-edited candidates. Track revisions, quantization, capability preservation and limitations.

mradermacher/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-GGUF

12B • Updated Jan 10 • 15.9k • 72
Stabhappy/gemma-4-31B-it-heretic-Gguf

31B • Updated Apr 4 • 2.14k • 16
coder3101/gemma-4-31B-it-heretic

Image-Text-to-Text • 31B • Updated Apr 14 • 2.06k • • 97
Youssofal/MiniMax-M2.7-Abliterated-Heretic-GGUF

Text Generation • 229B • Updated Apr 14 • 2.94k • 48