Sanchit Monga

sanmonga22's activity

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

New activity in runanywhere/qwen3_5_0_8b_HNPU 22 days ago

Add v75 (SM8650/Galaxy S24) W8 bundle

#5 opened 23 days ago by

flying101

New activity in runanywhere/canary_1b_flash_HNPU 23 days ago

v75 (Galaxy S24 / SM8650, soc_model 57): Canary-1B-flash FastConformer-AED ASR — device-validated " Hey, Jarvis."

#1 opened 24 days ago by

flying101

New activity in runanywhere/deepseek_r1_distill_qwen_1_5b_HNPU 23 days ago

Add generic chat block to v79 manifest (template-as-data)

#3 opened 24 days ago by

Aman0runanywhere

New activity in runanywhere/qwen3_5_4b_HNPU 23 days ago

Add generic chat block to v79 manifest (template-as-data)

#3 opened 24 days ago by

Aman0runanywhere

New activity in runanywhere/qwen3_5_2b_HNPU 23 days ago

Add generic chat block to v79 manifest (template-as-data)

#3 opened 24 days ago by

Aman0runanywhere

New activity in runanywhere/qwen3_5_0_8b_HNPU 23 days ago

Add generic chat block to v79 manifest (template-as-data)

#4 opened 24 days ago by

Aman0runanywhere

New activity in runanywhere/qwen3_vl_HNPU 23 days ago

v75 (Galaxy S24 / SM8650, soc_model 57): Qwen3-VL-2B VLM (vision) bundle — fp16 vision tower + W8 shared decode

#1 opened 24 days ago by

flying101

New activity in runanywhere/gemma4_e2b_HNPU 23 days ago

v75 (Galaxy S24 / SM8650, soc_model 57): Gemma-4-E2B text LLM — int8 decode + fp16 lm-head + PLE tables

#1 opened 24 days ago by

flying101

New activity in runanywhere/canary_qwen_2.5b_HNPU 23 days ago

v75 (Galaxy S24 / SM8650, soc_model 57): Canary-Qwen-2.5B LLM path (LoRA-merged Qwen3-1.7B backbone) — runs 13.4 tok/s; NOT a standalone text LLM (needs audio)

#1 opened 23 days ago by

flying101

New activity in runanywhere/qwen3_5_2b_HNPU 24 days ago

v75 (Galaxy S24 / SM8650, soc_model 57): Qwen3.5-2B W8-decode bundle — Plane A 6/6, 10.5 tok/s

2

#2 opened 25 days ago by

flying101

New activity in runanywhere/qwen3_5_4b_HNPU 24 days ago

v75 (S24/SM8650, soc 57): Qwen3.5-4B sharded-W8 decode bundle — Plane A greedy-correct, 3.8 tok/s

2

#2 opened 25 days ago by

flying101

New activity in runanywhere/qwen3_0_6b_HNPU 24 days ago

v75 (S24/SM8650, soc 57): Qwen3-0.6B W8-decode + fp16-prefill bundle — Plane A 6/6

2

#2 opened 25 days ago by

flying101

New activity in runanywhere/ternary_bonsai_1_7b_HNPU 24 days ago

v75 (S24/SM8650, soc 57): Ternary-Bonsai-1.7B W8 bundle — Plane A 6/6

2

#2 opened 25 days ago by

flying101

New activity in runanywhere/moonshine_tiny_HNPU 24 days ago

v75 (S24/SM8650, soc 57): Moonshine-tiny ASR bundle — Plane A 2/2, WER 0.0

2

#2 opened 25 days ago by

flying101

New activity in runanywhere/moonshine_base_HNPU 24 days ago

v75 (S24/SM8650, soc 57): Moonshine-base ASR bundle — Plane A 2/2, WER 0.0

2

#2 opened 25 days ago by

flying101

New activity in runanywhere/nemotron_nano_8b_HNPU 24 days ago

v75 (Galaxy S24 / SM8650, soc_model 57): Llama-3.1-Nemotron-Nano-8B 8-shard W8 bundle — export 8/8 (runtime needs >8GB RAM)

#1 opened 24 days ago by

flying101

New activity in runanywhere/deepseek_r1_distill_qwen_1_5b_HNPU 24 days ago

v75 (S24/SM8650, soc 57): DeepSeek-R1-Distill-Qwen-1.5B fp16 bundle — export 8/8 (runtime needs >8GB RAM)

2

#2 opened 24 days ago by

flying101

New activity in runanywhere/ternary_bonsai_1_7b_HNPU 25 days ago

Replace v79 bundle with QAIRT 2.45 build (loads on 2.45 app runtime)

#1 opened 28 days ago by

Aman0runanywhere

New activity in runanywhere/deepseek_r1_distill_qwen_1_5b_HNPU 25 days ago

Add v79 fp16 bundle (QAIRT 2.45; device-validated S25 — coherent, fp16 near-tie drift)

#1 opened 28 days ago by

Aman0runanywhere

New activity in runanywhere/qwen3_5_0_8b_HNPU 25 days ago

Add v79 W8 bundle (QAIRT 2.45; device-validated S25 3/3 greedy-exact, 22.7 tok/s)

#2 opened 28 days ago by

Aman0runanywhere