JT Flash 35B is Jt's language model. A 35B-parameter Flash-tier large language model from China Mobile, optimized for fast inference in enterprise deployments.
| Benchmarks | |
|---|---|
| Intelligence Index | #183 |
| GPQA | #130 |
| HLE | #318 |
| IFBench | #242 |
| Time to First Token | #173 |
| SciCode | #335 |
| LCR | #167 |
| TerminalBench Hard | #110 |
| TAU2 | #1 |
| Output TPS | #400 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host JT Flash 35B, ranked by cheapest on-demand price. The model needs about 84 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP20s |  Azure | 2× AMD Alveo U250 FPGA (64GB) | 128 GB | $3.30/hr | ||
| g7e.2xlarge |  AWS | RTX PRO Server 6000 | 96 GB | $3.36/hr | ||
| g2-standard-48 |  GCP | 4× nvidia-l4 | 96 GB | $3.99/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| JT-4.1 Flash 236B A21B Non-Reasoning | — | — | — | — | Available |
| JT Flash 35B | — | — | — | — | Current |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| JT-35B-Flash | Mini | — | — | — | — |
| JT-MINI | Mini | — | — | — | — |