cd /news/large-language-models/qwen-3-8-27b-on-rtx-5090-at-90-120tp… · home › topics › large-language-models › article
[ARTICLE · art-137623] src=gist.github.com ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

Qwen 3.8 27B on RTX 5090 at 90-120tps

A developer published a llama-server configuration that runs a Qwen 3.8 27B NVFP4 model with MTP speculative decoding on an RTX 5090, reporting throughput of 90-120 tokens per second. The setup uses a 262,144-token context with q4_0 KV cache quantization, flash attention, and a draft-mtp speculative type capped at four draft tokens.

by read1 min views1 publishedSep 22, 2026

| | llama-server \ |

|  | --alias qwen3.8-27b-nvfp4-mtp-q8attn \ | 
|  | -m "$HOME/.lmstudio/models/utautako/Qwen3.8-27B-NVFP4-MTP-Q8attn-GGUF/Qwen3.8-27B-NVFP4-MTP-Q8attn.gguf" \ | 
|  | --mmproj "$HOME/.lmstudio/models/utautako/Qwen3.8-27B-NVFP4-MTP-Q8attn-GGUF/mmproj-Qwen3.8-27B-NVFP4-BF16.gguf" \ | 
|  | --spec-type draft-mtp \ | 
|  | --spec-draft-n-max 4 \ |

| | -ngl 99 \ | | | -c 262144 \ | | | -ctk q4_0 \ | | | -ctv q4_0 \ | | | -b 2048 \ | | | -ub 512 \ |

|  | --host 127.0.0.1 \ | 
|  | --port 1234 \ | 
|  | --jinja \ | 
|  | --reasoning-effort low \ | 
|  | --kv-unified \ |

| | -t 12 \ | | | -np 1 \ |

|  | --flash-attn on \ | 
|  | --no-mmap |
source & further reading
gist.github.com — original article My global agents configuration for Pi Agent, Codex and DeepSeek Harness. Codex: autonomous Luna subagent, per-task reasoning effort, and completion callbacks gist:5dd77edf041418aabf2969fe49eeea43
── more in #large-language-models 4 stories · sorted by recency
── more on @qwen 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/qwen-3-8-27b-on-rtx-…] indexed:0 read:1min 2026-09-22 · —