gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090
image-text-to-text model by gittensor-model-hub
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Runs on SparkInfer, SGLang and vLLM unmodified — configs for all three are below. Serving many users at once? See concurrency. SparkInfer × this NVFP4 build × the DSpark v2 drafter — an engine, a checkpoint, and a speculative drafter optimized against each other, compounding to 4.3×. The drafter never changes what the model says: the target verifies every drafted token. GeForce RTX 5090–specific NVFP4 checkpoint of Qwen/Qwen3.8-27B, quantized with NVIDIA Model Optimizer. Serves the full native 262,144-token context on 32 GB. With the DSpark v2 drafter: 264.8 tok/s overall — up to 420 on code — on SparkInfer (its bench harness; the HTTP server is autoregressive-only today) and 161.7 tok/s on SGLang's OpenAI server. Without speculation: 92.9 tok/s SparkInfer · 85.8 SGLang. This is the final build. Everything is quantized down to the lmhead, the unused MTP head is removed from the weights, and the file ships as two…
Read the full model card ↗ · Preview checked 2026-10-30T21:20:05.720Z
Inside the original model card — Document outline
- RTX5090 Blackwell GPU Optimized Qwen-3.8-27B-NVFP4
- 420 tok/s writing code. One consumer GPU.
- Quick start — one docker run
- Tuning
- Speculative decode benchmark
- Building from source instead
- Performance
- Engines, same weights, identical prompts
- Measured against the other NVFP4 builds of this model
- Serving more than one user
- Repeated long prefixes: 19×
- SparkInfer + DSpark: 2.73× in the bench harness
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090 is a image-text-to-text model repository published by gittensor-model-hub on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 617,760
- Cumulative likes
- 172
- Hugging Face trending score
- 5
- Reported safetensors parameters
- 14,557,547,760
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-08-14T16:00:58.000Z
- Last modified
- 2026-09-10T01:49:07.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.8-27B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-03T06:39:36.097Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.