Qwen3.8-27B-Slipstream
Qwen3.8-27B (dense) for the Slipstream inference engine: our own NVFP4 quantization of the official BF16 weights with MSE-chosen block scales, MXFP8 prefill copies and the MTP head. Runs on one Spark (TP1) or two (TP2).
These are Slipstream weight files (weights.vbin + index.json per directory), the engine's own pre-packed format. They run only with Slipstream; they are not safetensors and do not load in other runtimes. Built with Slipstream's converters at commit 20c2dd9 (2026-10-31).
Base model: Qwen/Qwen3.8-27B. Engine: Slipstream (engine code release coming soon). Hardware: two NVIDIA DGX Spark (GB10, 128 GB each) connected over their 200 GbE link.
Contents
| Directory | What | Node |
|---|---|---|
qwen38_27b8 |
model weights for one Spark (TP1) | single Spark |
qwen38_27b8_tp2_r0 |
model weights, rank 0 (TP2) | first |
qwen38_27b8_tp2_r1 |
model weights, rank 1 (TP2) | second |
Download
On the first Spark (rank 0, runs the HTTP server):
hf download Interactify/Qwen3.8-27B-Slipstream --local-dir ~/vmodels --include "qwen38_27b8_tp2_r0/*"
On the second Spark (rank 1):
hf download Interactify/Qwen3.8-27B-Slipstream --local-dir ~/vmodels --include "qwen38_27b8_tp2_r1/*"
On a single Spark, download qwen38_27b8 instead:
hf download Interactify/Qwen3.8-27B-Slipstream --local-dir ~/vmodels --include "qwen38_27b8/*"
The tokenizer, chat template and generation config:
hf download Qwen/Qwen3.8-27B --exclude "*.safetensors" # on the first Spark
The directory names match the defaults in Slipstream's server/models.json, so no configuration is needed.
Run
python server/slipstream.py serve qwen3.8-27b
The server speaks the OpenAI and Anthropic APIs on port 8080. See the Slipstream README for profiles, the router and engine settings.
Measured on Slipstream
- Decode, one stream with MTP drafts: structured 119 / prose 71 / code 93 / JSON 103 tokens/s (serial 26).
- Prefill (MXFP8 W8A8): 1541 tokens/s at 16k.
- Quality: NLL +1.0 % against BF16 (512 tokens of English text), the same top-1 accuracy.
Notes
- Context up to 262,144 tokens.
- Slipstream runs this model from its
build-q35build (seeserver/models.json).
License
Apache 2.0, as the base model. See LICENSE and NOTICE.
Model tree for Interactify/Qwen3.8-27B-Slipstream
Base model
Qwen/Qwen3.8-27B