GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ginsongsong
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ginsongsong
Model Tree
Input Modalities
Output Modalities
Supported Functionality
quant_method=fp8, weight_block_size=[32, 32], expert_dtype=fp4).w8a8_fp8 with dynamic per-token activations.F32 [N, 1] .weight_scale).wo_a tensors remain in their source contracts.ptpc_conversion_manifest.json.This is a mixed FP4PTPC checkpoint, not a full W8A8 checkpoint and not the original DeepSeek release. Stock runtimes without DeepSeek-V4.1 gfx942 and mixed MXFP4/PTPC support may not recognize or execute this checkpoint correctly.
DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses.
| Benchmark | DS-V4.1-Flash-1017 | DS-V4.1-Flash | K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 |
|---|---|---|---|---|---|---|
| HLE w/o tools | 42.6 (44.0†) | 36.8 (39.1†) | 43.5 | 42.0† | 44.5 | 56.3 |
| Terminal-Bench 4.0 | 42.3 | 31.2 | 12.6 | 37.9 | 39.9 | 51.8 |
| DeepSWE v1.1 | 77.0 | 74.2 | 67.5 | 66.9 | 73.0 | 74.0 |
| ProgramBench | 29.1 | 20.3 | 17.5 | 19.0 | 23.0 | 37.0 |
| NL2Repo-Bench | 68.2 | 65.4 | 58.0 | 58.0 | 56.8 | 75.3 |
| Automation-Bench v1.0.6 | 60.5 | 54.8 | 46.7 | 48.8 | 45.8 | 50.3 |
| Agents’ Last Exam | 35.4 | 31.8 | 27.6 | 28.5 | 26.7 | 28.6 |
| Apex Bench v1.1 | 72.1 | 64.6 | 47.8 | 56.6 | 54.3 | 65.8 |
| Chartography (w/tools) | 83.0 | 78.9 | 68.1 | — | 79.9 | 84.0 |
| BabyVision (w/tools) | 92.5 | 89.6 | 85.7 | — | 88.9 | 94.1 |
| ZeroBench-main (w/tools) | 51.0 | 49.0 | 41.0 | — | 53.0 | 52.0 |
† denotes the text-only subset of HLE. We use the Claude Code harness for Terminal-Bench 4.0 and the Mini-SWE-V2 harness for DeepSWE v1.1.
This release does not include a Jinja-format chat template. The encoding folder contains a self-contained Python reference implementation (encoding.py) with test cases for multi-turn conversations, tool calling, thinking mode, numeric reasoning effort, mid-conversation system messages, and interleaved image content.
For production use, we additionally release deepseek-recipe, a set of Rust libraries with Python bindings that provides the same prompt format as a maintained, protocol-aware toolkit. It converts Messages, Chat Completions, and Responses API requests into the Conversation format, encodes them into DeepSeek V4 and V4.1 prompts or token IDs, and parses model output back into complete or streamed responses — covering thinking, tool calls, images, and generation settings. Model inference, tool execution, and HTTP transport are left to the caller.
Please refer to the inference folder for instructions on weight conversion and running inference locally.
Recommended sampling parameters:
| Parameter | Value |
|---|---|
temperature | 1.0 |
top_p | 1.0 |
context_window | 1M tokens |
max_tokens | ≥ 256K |
This repository and the model weights are licensed under the MIT License.
bibtex
@misc{deepseekai2026deepseekv41flash, title={DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression}, author={DeepSeek-AI}, year={2026},}If you have any questions, please raise an issue or contact us at service@deepseek.com.
@misc{deepseekai2026deepseekv41flash, title={DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression}, author={DeepSeek-AI}, year={2026},}