BUILDER DOSSIER / OTHER

Tech2wild

GitHub ↗@Tech2Wild ↗Independent builder

Discovered via New this weekUpdated 21h ago273 GitHub followers

THE WORK, IN THEIR CORNER OF THE INTERNET

decoding what they build_

WHY THEY’RE ON OUR RADAR

GLM-5.3-Flash-NVFP4-DFlash2-2x-DGX-Spark got 191 stars in 31 days

Be the first to back @Tech2Wild

Nobody has launched a Paid coin for this dev yet. Launch one and 80% of its trading fees go to @Tech2Wild in dollars on X. Takes about a minute.

1
Copy this line for the coin's description
Fees to @Tech2Wild via UsePaid
This exact line is how Paid knows who to pay. Don't change it.
2
Launch it on Paid
OPEN PAID →ticker idea: $DEEPSEEKV4
Paste the line into the description. Paid sets 100% of creator fees to its treasury, then pays @Tech2Wild. How Paid works
3
Come back and check
Launched it? We'll confirm with Paid and put it on the board.
4
Tell CT
Share the card below so people find the coin (and the dev notices).

Share this scout

Post this card on X. The link unfurls into the card automatically, so your followers see the stats.

Download image

Their projects

★ = stars, like likes from other developers. + = new stars since our last scan.

DeepSeek-v4-Flash-Vision-Exp-DSpark-1M-NVFP4-KV-2x-DGX-Spark★ 486

DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark

Python · started 89d ago · last update 16d ago

GLM-5.3-Flash-NVFP4-DFlash2-2x-DGX-Spark★ 191

GLM-5.3-Flash (NVFP4) on 2x NVIDIA DGX Spark - vLLM TP2, 262K context, MTP. World-first deploy recipe: 7 day-0 bugs found and fixed, patched sm121 image, probes and full report.

Python · started 31d ago · last update 2d ago

Qwen3.8-Flash-Next-NVFP4-DGX-Spark★ 125

Qwen3.8-Flash-Next (NVFP4) on DGX Spark in vLLM: one Spark 43.9 tok/s with our disk-backed n-gram table patch, staged gather and reduced-vocab MTP draft; TP2 SPEED 53.7; TP4 CONTEXT 9M KV pool. Launchers, patch, 40-prompt harness, KV ledger, credits. SGLang TP2 day-0 lane kept.

Python · started 31d ago · last update 19d ago

DeepSeek-V4.1-Flash-vLLM-DGX-Spark★ 86

DeepSeek-V4.1-Flash (552B MoE, MXFP4 experts, 1M ctx) on four NVIDIA DGX Sparks with vLLM TP4: Engram-on-disk patch, sm121 kernel build, launchers, measured numbers

Python · started 16d ago · last update 7d ago

Deepseek-v4-Flash-TP2-DGX-Spark-500k-CTX★ 83

Working recipe to serve DeepSeek-V4-Flash across two NVIDIA DGX Spark (GB10) nodes with vLLM (TP=2, FP8 KV, MTP) over a RoCE/RDMA link — Docker image, launch scripts, RDMA/NCCL setup, and the gotchas.

Shell · started 112d ago · last update 76d ago

GLM-5.2-QuantTrio-200K-4x-DGX-Spark--36tok-s★ 77

Recipe: GLM-5.2 (unpruned QuantTrio Int4-Int8Mix) at 200K ctx with MTP spec decode on a 4x NVIDIA DGX Spark (GB10) cluster

Python · started 84d ago · last update 63d ago

MiniMax-H3-Local★ 50

Run MiniMax H3 locally: a full 15s clip with audio on a single RTX 3090. The fix is one flag.

Shell · started 54d ago · last update 53d ago

MiniMax-M3-2x-DGX-Spark-36-tok-s★ 46

MiniMax-M3 (428B, no pruning) at 36 tok/s on 2× NVIDIA DGX Spark — W4A16 GPTQ + NVFP4 KV + EAGLE-3 speculative decoding on vLLM. Three serving lanes: speed / balanced / long-context.

— · started 83d ago · last update 76d ago