estimate
Can I run Qwen3.8-27B on an RTX 5090?
Yes, fully in VRAM (estimate)
Can I run Qwen3.8-27B on an RTX 5090? Yes, fully in VRAM (estimate). About 17.8 GB at Q4_K_M (estimate).
VRAM per quant for Qwen3.8-27B
Updated . The later of the hardware price date and the formula date.
| Quant | Context | Weights | KV | Overhead | Total | Usable | Fit | Est. tok/s |
|---|---|---|---|---|---|---|---|---|
| Q4 Q4_K_M | 8,192 tokens | 16.5 GB measured GGUF file size | 0.5 GB estimate | 0.8 GB estimate | 17.8 GB estimate | 31.4 GB estimate | full | 81 tok/s estimate |
| Q5 Q5 (~0.71 bytes/param) | 8,192 tokens | 19.7 GB estimate | 0.5 GB estimate | 0.8 GB estimate | 21.1 GB estimate | 31.4 GB estimate | full | 68 tok/s estimate |
| Q8 Q8 | 8,192 tokens | 29.7 GB estimate | 0.5 GB estimate | 0.8 GB estimate | 31.1 GB estimate | 31.4 GB estimate | full | 46 tok/s estimate |
| FP16 FP16 | 8,192 tokens | 55.6 GB estimate | 0.5 GB estimate | 0.8 GB estimate | 56.9 GB estimate | 31.4 GB estimate | no | — |
| Q4, longer context | 32,768 tokens | 16.5 GB measured GGUF file size | 2.1 GB estimate | 0.8 GB estimate | 19.4 GB estimate | 31.4 GB estimate | full | 74 tok/s estimate |
Formula estimate, not a benchmark. Method →
community measurement, not ours
Canonical single-GPU figures on that results page: mean of five runs, one RTX 3090, the other replica stopped, the ~1K-token prompt column, 512-token greedy completions, reasoning disabled, 250 W power cap. The page says every rung is the same 4-bit checkpoint. llama.cpp out of the box 27.6 tokens per second; llama.cpp tuned (FA + q8 KV + MTP) 42.6; stock vLLM + MTP k=4 85.6; patched vLLM + MTP k=4 167.8; patched vLLM + DFlash2 k=7 212.1. The page dates the single-replica correction 31 August. results.html was last committed on 18 September 2026, which is the published date stored here. Not a localLLMrig measurement. Calculator estimates keep benchmarkSourceUrl null.
| Hardware | Tokens per second |
|---|---|
| RTX 3090, llama.cpp out of the box | 27.6 tok/s community measurement, not ours |
| RTX 3090, llama.cpp tuned (FA + q8 KV + MTP) | 42.6 tok/s community measurement, not ours |
| RTX 3090, stock vLLM + MTP k=4 | 85.6 tok/s community measurement, not ours |
| RTX 3090, patched vLLM + MTP k=4 | 167.8 tok/s community measurement, not ours |
| RTX 3090, patched vLLM + DFlash2 k=7 | 212.1 tok/s community measurement, not ours |
Qwen3.8-27B on RTX 3090, published 2026-09-18
This measurement stays separate from the formula estimate above.
Cheapest catalog option that fits at Q4
GeForce RTX 3090 24GB, used (median of sold listings), €1,224, dated 2026-10-16. No buy link.
This hardware
$7,052€6,299
new (lowest in-stock EU)
price as of 16 Oct 2026
PriceSquirrelCheapest in-stock listing on 16 Oct 2026: €6,299, ASUS ROG Astral GeForce RTX 5090 32GB OC White at Proshop (FI). MSI Gaming Trio OC at Compumsa (BE) was €6,571 and out of stock. A 16 Oct 2026 fact-check notes BE/NL/DE about €7,900–€8,800. No used median was recorded. NVIDIA (Jeff Fisher, 16 Oct 2026) denies a production halt; supply is tight and some retailers have delisted the card.
Embed this
Qwen3.8-27B on RTX 5090
[](https://localllmrig.com/can-i-run/qwen3.8-27b/rtx-5090?utm_source=badge)
Questions
- Can I run Qwen3.8-27B on an RTX 5090?
- Yes, fully in VRAM (estimate).
- How much memory does Qwen3.8-27B need at Q4?
- About 17.8 GB at 8,192 tokens (estimate): 16.5 GB weights (measured GGUF file size), 0.5 GB KV cache, 0.8 GB overhead.
- How fast is Qwen3.8-27B on RTX 5090 (estimate)?
- About 81 tok/s at Q4 (estimate, not a benchmark).
Rig Report waitlist
A written hardware plan for one model and budget. Planned price, not for sale yet.
Sign up with consent and download GPU Buying Cheat Sheet (EU, Oct 2026). The file is not emailed.
Read next: Building a local LLM rig in the RAMageddon.