Joe lafrite

joelafrite's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 6 days ago

dealignai/DeepSeek-V4.1-Flash-UNCENSORED-EXL3-2.9bpw

Image-Text-to-Text • 105B • Updated 9 days ago • 880 • 34

liked a model 8 days ago

RedHatAI/GLM-5.3-Flash-NVFP4

Image-Text-to-Text • 169B • Updated 8 days ago • 60k • 39

liked a model 15 days ago

deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated 16 days ago • 641k • • 3.76k

liked a model 25 days ago

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

Image-Text-to-Text • 305B • Updated 25 days ago • 925k • • 928

New activity in gratex/Qwen3.8-27B-DFlash2-W4A16-g128-sym-GPTQ 25 days ago

apply_dense_kv_fix.py: silent corruption risk with NVFP4 drafters (+ working variant)

3

#1 opened 27 days ago by

joelafrite

updated a model 25 days ago

joelafrite/Qwen3.8-27B-fp8-KV-scale-calibration

Updated 25 days ago

published a model 25 days ago

joelafrite/Qwen3.8-27B-fp8-KV-scale-calibration

Updated 25 days ago

liked 6 models 26 days ago

unsloth/GLM-5.3-Flash-GGUF

Text Generation • 321B • Updated 20 days ago • 910k • 430

unsloth/Qwen3.8-27B-GGUF

27B • Updated Aug 20 • 6.83M • 4.64k

unsloth/Qwen3.8-Flash-Next-GGUF

Image-Text-to-Text • 177B • Updated 24 days ago • 1.72M • 1.07k

zai-org/GLM-5.3

Text Generation • 753B • Updated 22 days ago • 1.28M • • 1.93k

zai-org/GLM-5.3-Flash

Image-Text-to-Text • 321B • Updated 19 days ago • 4.24M • • 2.57k

Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated about 1 month ago • 1.07M • • 5.71k

liked 2 models 27 days ago

LibertAIDAI/GLM-5.3-Flash-NVFP4

Image-Text-to-Text • 165B • Updated 27 days ago • 55.4k • 67

gratex/Qwen3.8-27B-DFlash2-W4A16-g128-sym-GPTQ

2B • Updated 26 days ago • 367 • 1

New activity in LibertAIDAI/GLM-5.3-Flash-NVFP4 27 days ago

Datapoint: fp4 vs fp8 GLM-5.3-Flash endpoint parity on GSM8K + HumanEval

#8 opened 27 days ago by

joelafrite

New activity in QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4 28 days ago

Heads-up: config declares an MTP head but no mtp.* tensors ship (silent 0%-acceptance trap) — and a working graft recipe

3

#3 opened 28 days ago by

joelafrite

New activity in peculiar-ragdoll/Qwen-Sharp-Chat-Templates 28 days ago

Production adoption report (vLLM + MTP): terseness confirmed, quality up at n=4 — and the MTP think-leak did NOT reproduce

❤️ 1

1

#11 opened 28 days ago by

joelafrite

New activity in orcarouter/Qwen3.8-27B-Uncensored-NVFP4 28 days ago

vLLM boot failure: quantization target literal `lm_head` never matches — one-line fix

1

#3 opened 28 days ago by

joelafrite

New activity in RadixArk/Qwen3.8-27B-DSpark 28 days ago

v2 validated on vLLM + NVFP4 target (RTX 5090): AL ~3.22 confirms your claim — with a 32GB context warning

#8 opened 28 days ago by

joelafrite