What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
JetBrains released Mellum-4b-base in April 2025 as an openly distributed, 4-billion-parameter model built specifically for code completion—not as a general-purpose chat assistant. Its Apache 2.0 license and published serving examples make it available to developers and researchers who want to inspect, adapt, or run a focused code model. JetBrains later introduced Mellum2, a distinct model with a broader natural-language and code scope.
What JetBrains released
JetBrains announced the original Mellum in April 2025 and published its base checkpoint, JetBrains/Mellum-4b-base, on Hugging Face. The company describes it as a 4B-parameter model trained from scratch for code completion in JetBrains IDEs, rather than a fine-tune of an existing open model. JetBrains’ announcement puts its purpose succinctly: “Mellum doesn’t try to know everything. It’s designed to do one thing really well: code completion.” (JetBrains’ announcement)
JetBrains calls this a “focal model”: a model deliberately built around a defined task rather than broad, general-purpose ability. For Mellum, that task is predicting code that fits into a developer’s editing context. It is not, by itself, a plug-and-play coding assistant with chat, tool use, or a finished IDE workflow.
What languages and tasks it targets
JetBrains lists support for Java, Kotlin, Python, Go, PHP, C, C++, C#, JavaScript, TypeScript, CSS, HTML, Rust, and Ruby. The model card describes Mellum-4b-base as a Llama-style base model, trained and uploaded in bf16 precision, with an 8,192-token context window and more than 4 trillion training tokens according to JetBrains’ 2025 materials. (Model card)
Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →#1 Best Overall
- Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
- Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
- Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
- Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
- 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.
“Base model” matters here: the checkpoint is not fine-tuned for downstream tasks out of the box. Teams can use it as a starting point for supervised fine-tuning or reinforcement learning, but applications beyond code completion may require adaptation and integration work.
How Mellum performed in JetBrains’ published evaluations
The figures below are results reported by JetBrains for the named checkpoints and benchmarks in the Mellum model card; they are not independent test results or a guarantee of production performance.
Rank #2
- 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
- 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
- Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
- 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
- What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.
| Checkpoint | Benchmark and subset | Reported result |
|---|---|---|
| Mellum-4b-base | HumanEval Infilling, pass@1 | 66.21% single-line; 38.52% multi-line; 29.70% random-span |
| Mellum-4b-base | SAFIM, pass@1 | 38.11% average |
| Mellum-4b-base | RepoBench 1.1, Python subset | 25.91% average across context-length settings |
| Python SFT variant | SAFIM, pass@1 | 42.12% average |
| Python SFT variant | RepoBench 1.1, Python subset | 28.37% average across context-length settings |
The SFT scores belong to a separate fine-tuned variant, not the base checkpoint. Benchmark results also depend on task format, data, and evaluation setup; a score on infilling or repository completion does not establish that a model is better for every coding workflow.
JetBrains separately described an internal evaluation using its BigCode benchmark dataset, covering popular supported languages including Python, Kotlin, and Java. The company says it checked for overlap with training data and examined slices such as repository age and activity to study performance and possible contamination. That account documents JetBrains’ own methodology, not third-party validation. (JetBrains’ training and evaluation discussion)
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchPC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Rank #3
- Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
- Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
- Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
- Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
- What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.
How to use Mellum-4b-base
The Hugging Face card lists the model under the Apache License 2.0 and provides examples for Transformers, vLLM, and SGLang. It also points to Docker, local applications, and quantized versions. Check the current model card for the exact code and supported software versions before deployment, since serving stacks evolve. (Mellum-4b-base model card)
For vLLM, the card’s serving example uses the checkpoint name JetBrains/Mellum-4b-base. A typical workflow is to install a compatible vLLM release, load that checkpoint with vLLM’s serving interface, then send completion prompts in the format your application expects. The card’s examples and compatibility notes should be treated as authoritative for the current invocation; hardware requirements are not specified in the cited materials, so no particular GPU or minimum VRAM can be promised here.
Rank #4
- Dual Converters, Infinite Potential：Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
- Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
- Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
- Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
- Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
Because this is a base completion model rather than an instruction-tuned chat model, a generic chat prompt may not produce a polished assistant response. Integrators should test prompts and output handling against the completion use case, and perform their own validation before putting suggestions into an IDE or automated workflow.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Who the original Mellum is—and isn’t—for
- A plausible fit: researchers, educators, and advanced teams evaluating a focused code-completion model, adapting a base checkpoint, or integrating it into a controlled development environment.
- Not an automatic fit: anyone expecting a ready-made conversational coding assistant, a drop-in replacement for an IDE’s complete AI feature set, or secure code without review.
- Deployment choice: local or self-hosted inference can give an organization more control over infrastructure, but it does not make model-generated code inherently safe.
JetBrains warns that Mellum may reflect biases in public codebases and that suggestions should not be assumed secure or free of vulnerabilities. Review generated code, apply normal security checks, and assess whether the model and its deployment meet your organization’s requirements. (Model card limitations)
Recommended Free Tools
Best Value
- 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
- Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
- Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
- HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
- What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
How Mellum2 differs from the 2025 release
In June 2026, JetBrains announced Mellum2 as a later model with a broader stated scope. JetBrains describes it as a non-multimodal model trained on natural language and code, with 12 billion total parameters and 2.5 billion active parameters per token through a mixture-of-experts design. Its named use cases include prompt routing and orchestration, retrieval-augmented generation, fast sub-agents, and private or local AI deployment. These are Mellum2 details; they should not be read as capabilities or benchmark results for Mellum-4b-base. (JetBrains’ Mellum2 announcement)
JetBrains says Mellum2 was trained on more than 10 trillion tokens, describing an initial stage of about 6 trillion tokens and another 2.8 trillion-token stage focused strongly on coding. Those are the company’s training figures, not an independently audited count. The announcement also characterizes Mellum2 as competitive with similarly sized models while taking less than half the inference time; that speed statement is JetBrains’ claim and depends on the benchmark setup, so it should not be generalized into a universal latency result.
JetBrains’ AI service-provider page, updated September 29, 2026, lists Mellum and Mellum2 as separate JetBrains-trained models and marks both Apache License 2.0. For those models hosted on that platform, JetBrains says they run on JetBrains infrastructure and that inputs and outputs are not shared with the parties that trained them. That statement applies to the listed hosted models and platform, not every local deployment or third-party model. (JetBrains AI service providers)
Bottom line for developers
The original Mellum is best understood as an openly licensed, 4B-parameter code-completion base model, useful to people prepared to evaluate or adapt it—not as a turnkey general-purpose assistant. Its published benchmark numbers are JetBrains’ own and should be read with their checkpoint and task labels intact. Mellum2 is a later, broader model; choosing between them depends on whether the need is focused completion or the newer model’s stated natural-language and code workflows.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
