DGX Spark
Qwen3.8-Flash-NextMost runSolo load79.5- Qwen3.8-27B27B, SGLang72
Ling-3.0-Flash
GLM 5.3 FlashEXL3 K2, one box18.6
Open weights. Uncensored models.
Private inference.
Open to everyone.
Choose your model and where it runs. Run locally to keep prompts on your device, or use independent hosts on the network.
Hosts keep 80% of each completed job. You choose your rate.
No chat logs. Prompts are erased when a host picks them up. Replies are erased 10 minutes after they finish. We keep only token counts for billing. How privacy works
Your model. Your call.
Text inference on the network. Image, voice, and audio models to explore locally.
- Text & codeOn the network
- ImagesExplore locally
- VoiceExplore locally
- Speech-to-textExplore locally
- AudioExplore locally
Live now
All models & prices →Checking availability…
Rates apply to input and output tokens. Host-reported speed; endpoint checks do not verify model weights.
TRENDING
- 1
DeepSeek v4.1 FlashHOT - 2Empero Qwen3.8-35B-A3BHOT
- 3
Gemma-4 26B UncensoredHOT - 4Gemma-4 26B-A4B-itHOT
- 5GLM 5.3 FlashHOT
STREET · DGX SPARK
Sample data · 2026-10-03
$8,050▼ 6.7% 7d
TAPE
@fillagrew “351 tokens/sec on Qwen3.5 2B at Q4_K_M”
@Youssofal_ “Peak Speed: 126.5 TPS.”
Street stacks
since Sep 20
DGX Spark
- GLM 5.3 FlashDefaultGLM on both60.4
- GLM 5.3 FlashTensorFold, 4 streams60.4
- DeepSeek v4.1 Flash
- Qwen3.8-Flash-Next45
MiMo-V2.6-Flash
DGX Spark
- GLM 5.3 FlashHer deskAll three
- GLM 5.3 Flash · Qwen3.8-Flash-NextGLM orch on 2×, Qwen worker on 1×
- DeepSeek v4.1 FlashHomogeneous
- GLM-5.2NVFP4
DGX Spark
- GLM 5.3 Flash · Qwen3.8-Flash-NextGLM orch 2× + Qwen worker 2×
- GLM 5.3 FlashHomogeneous
- DeepSeek v4.1 FlashHomogeneous
DGX Spark
- GLM 5.3 Flash · Qwen3.8-Flash-Next · DeepSeek v4.1 FlashHeard mostGLM orch + Qwen worker + DeepSeek scanner
Uncensored31
Every liberated weight. A number is a quoted tok/s.
Quoted
No quote yet
- 4DeepSeek v4.1 Flash abliterated—
- 5
Flash-Next RVN— - 6Gemma-4 12B OBLITERATED—
- 7Gemma-4 26B Abliterix—
- 8Gemma-4 26B Uncensored—
- 9Gemma-4 31B Uncensored—
- 10GLM 5.3 EXL3 abliterated—
- 11GLM 5.3 Flash abliterated—
- 12GLM 5.3 Flash Uncensored—
- 13GLM 5.3 Uncensored—
- 14Huihui Qwen3.8-27B—
- 15Qwen-Image-2.1 Uncensored—
- 16Qwen3.8-27B Aggressive—
- 17Qwen3.8-27B Coletti—
- 18Qwen3.8-27B Fable—
- 19Qwen3.8-27B Heretic—
- 20Qwen3.8-27B Heretic ARA—
- 21Qwen3.8-27B KCRN—
- 22Qwen3.8-27B Mythos—
- 23Qwen3.8-27B NoRefusal—
- 24Qwen3.8-27B OBLITERATED—
- 25Qwen3.8-27B Splash—
- 26Qwen3.8-27B Twin Turbo—
- 27Qwen3.8-27B Ultra Heretic—
- 28Qwen3.8-27B Uncensored—
- 29Qwen3.8-35B-A3B APEX—
- 30Qwen3.8-9B Heretic—
- 31SuperQwen3.8-27B—
Payback ranked
US price. Each model at its suggested price, host keeps 80%. 20% duty. Left is faster.
| 1 | Gemma-4 26B-A4B-it · RTX 5090 32GB | 17 mo | 71% |
| 2 | Qwen3.8-27B · RTX 5060 Ti 16GB | 2.1 yr | 47% |
| 3 | Qwen3.8-27B · RTX 5060 Ti 16GB | 2.7 yr | 37% |
| 4 | Qwen3.5 2B · RTX 5090 32GB | 2.9 yr | 34% |
| 5 | Qwen3.8-27B · DGX Spark | 3.4 yr | 30% |
| 6 | Qwen3.8-27B · DGX Spark | 4.9 yr | 20% |
| 7 | Qwen3.6-35B-A3B · M4 Pro | 5.3 yr | 19% |
| 8 | Qwen3.5-4B · M4 Pro | 5.5 yr | 18% |
Articles
2026-09-28How to bench a cyber weightA cyber bench ranks a published decode, with the publisher's name on the row. The first shelf is /cyber. This desk did not remeasure it.
2026-09-28A shell is not a weightMikko Haapoja posted one line and a link. The link is NVIDIA OpenShell. It keeps an agent inside a policy. It does not serve a model, and this desk did not run it.
2026-09-24Which box pays backStreet price comes back only if the tokens, at $1 per million, beat the watts. A Spark bought to resell that rate does not.
2026-09-23Inference, not a JEPAA decode tok/s figure is a serving number. Training a JEPA, or drawing a picture, wants a different machine.
2026-09-22The interface is the argumentThe home rank, the pool shelf, and the pair page are the argument. The desk shows those. It does not show the chain.