DeepSeek Coder 7B Instruct V1.5 is an open-source, decoder-only transformer model created by DeepSeek. It is a chat model designed for code generation, tabular verification, and structured reasoning tasks.
Input
Output
Context
4K
Max Output
512
Parameters
6.9B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
Download 13.8 GB · Runs on vLLM v0.32.0 · 11 GGUF builds
| Precision | Weights | One request at 4K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 12.9 GB | 14.0 GB | 1x NVIDIA T4 (16 GB) |
| INT8 | 6.44 GB | 7.19 GB | 1x NVIDIA T4 (16 GB) |
| INT4 | 3.22 GB | 3.81 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 6,910,365,696 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Public resources
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
DeepSeek Coder 7B Instruct V1.5 has a context window of 4,096 tokens and a maximum output of 512 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. DeepSeek Coder 7B Instruct V1.5 is an open-weight model under the Other license. You can download and self-host it within the license terms.
DeepSeek Coder 7B Instruct V1.5 has 6,910,365,696 parameters (6.9B), as stated in the creator's Hugging Face repository.
Limitations: Short context window: 4,096 tokens. Each is computed from the model's stated facts and benchmark results.
DeepSeek Coder 7B Instruct V1.5 accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for DeepSeek Coder 7B Instruct V1.5 yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves DeepSeek Coder 7B Instruct V1.5, and Inferbase runs it on your account with the same routing and logs.
The weights take 12.9 GB at FP16 / BF16, 6.4 GB at INT8, 3.2 GB at INT4, computed from the 6,910,365,696 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
Start on the free plan with 5,000 requests a month, no card required.