More
Submit build

Builds / NVIDIA L4 24 GB

NVIDIA L4 24 GB (72 W): Qwen3.8 27B stock llama.cpp 14.9 tok/s vs DSpine drafter 47.3 vs tqLLM 67.0 at 32K context

Last updated:

Source: vramcalculator.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
GPU(s)
NVIDIA L4 24 GB
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)
24
CPU
not stated
Motherboard
not stated
RAM
not stated
PSU
not stated
Other
23,034 MiB usable with ECC on, 72 W limit (median draw 71.4-71.9 W in every row, peak 78.03 W); cloud notebook session
Reported total cost
not stated
Power
72 W card limit

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Qwen3.8 27BUD-IQ4_XS (Unsloth, 14.25 GB), q8_0 KVllama.cpp (stock)14.9729 (prompt length not stated)context: 32K context row, one request📏 Median of 3 greedy runs, answers capped at 256 tokens; 12.98 tok/s at 64K, 10.11 at 128K; TTFT 33.04 s at 32K, 82.36 s at 64K, 227.73 s at 128K
Qwen3.8 27BUD-IQ4_XS (Unsloth, 14.25 GB) + Tencent DSpine-b16 drafter (1.26 GB)llama.cpp fork (Ajay9o9 dspine branch)47.25718 (prompt length not stated)⚡ spec-decode (DSpine (n-max 15))context: 32K context row, one request📏 Median of 3 greedy runs; 27.09 at 64K (n-max 15), 21.18 at 128K (n-max 7); prefill within 1.5% of stock
Qwen3.8 27BTQ3_4S TurboQuant (14.5 GB, different weights) + DFlash2 drafter (0.79 GB)tqLLM 1.4.4 (engine 9a9e7e5)66.97691 (prompt length not stated)⚡ spec-decode (DFlash2)context: 32K context row, one request📏 Median of 3 greedy runs; 61.59 at 64K; 20.94 at 128K because 3.09 GB of KV plus the LM head and embeddings moved to host memory on this 23,034 MiB card

Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 ÷ prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.

First-party run by vramcalculator.com (published 10 Nov 2026, updated 14 Nov). Three stacks on one card: stock and DSpine share the same weights; tqLLM uses its own TurboQuant file, so that row compares stack against stack, not bytes against bytes. Three runs of one prompt per size, not a quality test. The DSpine and tqLLM 3090 figures in the same article are the authors' own claims and are not listed here.

Source: https://vramcalculator.com/qwen3-8-27b-dspine-tqllm/

Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.

Embed this result

Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds — numbers stay on the build page.

Markdown

[![Measured on RigBase](https://getrigbase.com/badge/nvidia-l4-24gb-qwen38-27b-stock-dspine-tqllm-vramcalculator.svg)](https://getrigbase.com/builds/nvidia-l4-24gb-qwen38-27b-stock-dspine-tqllm-vramcalculator/)

HTML

<a href="https://getrigbase.com/builds/nvidia-l4-24gb-qwen38-27b-stock-dspine-tqllm-vramcalculator/" rel="noopener"><img src="https://getrigbase.com/badge/nvidia-l4-24gb-qwen38-27b-stock-dspine-tqllm-vramcalculator.svg" alt="Measured on RigBase" height="20"/></a>

Preview: Measured on RigBase · How to use

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

Speculative-decoding rows on this page are not like-for-like with plain decode. See how much MTP and DFlash really speed things up (measured pairs).