qwen38-mtp
qwen38-mtp is your card missing? run the a/b, open a pr. It is ranked #802 on the Dev Radar, in AI dev tools, first seen 6 days ago and shared in 3 posts (37.8k views).
What qwen38-mtp says about itself
One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, paired benchmarks, probe tool. - sudoingX/qwen38-mtp
GitHub - sudoingX/qwen38-mtp: One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, paired benchmarks, probe tool. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} sudoingX / qwen38-mtp Public Notifications You must be signed in to change…
What people said about qwen38-mtp on X
a contributor put two used rtx 3060 12gb cards on one board, and ran qwen 3.8 27b dense at 131k context. 34.2 tok/s stock, 58.9 tok/s with the flag, +72%, on 24gb of vram that costs less than one used 3090 on marketplace. the same pair on the unsloth q4 file at 64k: 30.0 tok/s to 53.3 tok/s, +78%, within a hair of a…
— @sudoingX, 4 days ago · 165 likes · see the post
a 3090 capped at 250w does 51 tok/s with the flag. the same card at 275w does 62 tok/s. one slider, +22%, for 25 watts. the same contributor tested two quants on that card the same day, Q4_K_M against Dynamic 3.0: 52.8 tok/s vs 52.9 tok/s, a tie. the power limit moved the number more than the file did. if you are…
— @sudoingX, 4 days ago · 62 likes · see the post
this is every card in the table with the mtp flag on and tok/s alone does not tell you if the card holds your context. here i grouped by the window it actually served at that speed, 73 rigs submitted in my open repo, five rows landed this morning. 262K > rtx 5090 32gb, UD-Q4_K_XL: 74.3 tok/s → 179.7 tok/s (n4) > rtx…
— @sudoingX, 6 days ago · 39 likes · see the post
Alternatives to qwen38-mtp
- muse.ai — New connectors are live today. Come build with us.
- classifier.dev — now outperforms jev and is free
- mimo-v2.6 RL — Streaming the run
- academy.dair.ai — Chat with Paper
- Union Alpha — Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level…
- cua — Draft #3943
qwen38-mtp in numbers
- Rank on the Dev Radar: #802 of 1500
- Shared in 3 posts by 1 account: @sudoingX
- 37.8k views on those posts
- First seen 6 days ago, last shared 4 days ago
- Pricing seen by Jev: open source
- Market: AI dev tools
FAQ
What is qwen38-mtp?
your card missing? run the a/b, open a pr It was first shared on X 6 days ago and is ranked #802 on the Dev Radar.
Is qwen38-mtp free?
It is open source.
Who shared qwen38-mtp?
1 account on X, including @sudoingX, in 3 posts totalling 37.8k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 13.5k posts from 4.7k X accounts over the last 21 days, 1.5k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 19:24 UTC. Full method.