new model · 2026.10.23
Last updated
Flint local LLM: can an open 40B coding agent run on a personal PC?
Check whether an open coding-agent model is usable on your own hardware
Flint is a mixture-of-experts model for coding agents published by Recursive in October 2026. It has 39.8B total parameters, about 2.5B active per token1, and a 262,144-token context. Recursive reports 54.9% on Terminal-Bench 2.1, 89.7% on SWE-bench Pro v2 and 74.2% on SWE-bench Verified. Its official instructions assume a single B300 or H200 GPU2, and Transformers modelling code is not included yet. Running it on a personal PC needs separately published GGUF3 weights and a llama.cpp-class runtime4, whose performance may differ from the vendor figures.
An agent model that inspects a codebase itself
Flint is a coding-agent model that reads a repository, fixes bugs, implements features and writes tests. It handles text input and output, reasoning, and multi-turn tool use. Its architecture is a decoder-only MoE5 Transformer6: of 49 layers, 2 are dense and 47 are MoE layers. Each MoE layer selects 6 of 256 experts, plus one shared expert that always runs.
Attention7 is split: 35 layers use a short 513-token window and 14 layers use full attention. The short-window layers hold a smaller KV cache8, which reduces the memory cost of long conversations. The 262,144-token context counts prompt9 plus generated output.
To use an open coding agent on a personal PC, check the runtime before the model scores. This article follows that order.
The official runtime is a server GPU
The vendor's documented path is SGLang, not GGUF or llama.cpp. You download about 80 GB of weights, build the SGLang image, and start a server on one B300 or H200 GPU. The address binds to 127.0.0.1, and /health_generate reports readiness. The model card states that Transformers modelling code is not yet included.
These instructions were not written with a personal PC in mind. B300 and H200 are data-centre GPUs whose memory configurations differ sharply from what an individual buys. On personal hardware you must use the separately published quantized GGUF, which runs on a different engine from the one the vendor measured.
Read the measurement conditions behind the scores
The vendor reports 54.9% on Terminal-Bench 2.1, 89.7% on SWE-bench Pro v2 and 74.2% on SWE-bench Verified. The model card also states the evaluation conditions: temperature 1.0, top-p 0.95 and top-k 20, with Terminus 2 for Terminal-Bench and the mini-swe-agent harness for SWE-bench. Agentic scores average pass@1 over at least five attempts.
The model card also states the limits of comparison. Evaluation setups vary by source, and among the tabulated scores the ones Recursive measured itself are marked. Flint's Terminal-Bench score applies an adjustment that counts solutions obtained through web retrieval as failures, while developer-reported scores may omit that adjustment. Keep that difference in mind when reading two numbers side by side.
On personal hardware, check support first
Two things come first on a personal PC. One is whether your runtime supports this architecture. Flint uses sliding-window attention across 35 layers, learned attention sinks and per-head RMSNorm, which differ from a typical llama-family model. Unless the runtime's documentation confirms these are implemented, the file may load poorly or not at all.
The other is memory. Quantizing 39.8B of weights to 4 bits still needs roughly a quarter of the original size. Using the full 262K context adds a KV cache even though only the selected experts compute. Start with short code reviews and increase context gradually to see how much headroom remains.
Consider the agent harness and permissions together
A coding agent's score does not come from the model alone. Which harness reads files, runs commands and retries failures is part of the result, and the vendor states it used the mini-swe-agent harness. To expect similar scores in your setup, match both the harness and the tool permissions.
An agent can run shell commands. Connected to a repository without a sandbox10 or allowlist11, it can delete or transmit files by accident. Even in a personal repository, check for sensitive keys first and narrow the execution permissions.
Check the licence and redistribution terms
Flint is released under the Apache 2.0 licence. Modification, redistribution and commercial use are permitted with no revenue threshold, but Apache 2.0 also requires keeping copyright notices, marking changes and honouring the patent clause. When embedding it in a team tool or redistributing it, keep the NOTICE and licence files with it.
Terminology notes
Token — A unit into which a model divides input or output for processing.
Back to the textGPU — A processor designed to handle many calculations in parallel. It performs model computations during AI inference.
Back to the textGGUF — A file format for model data, widely used by llama.cpp-based tools.
Back to the textRuntime — The software environment that provides facilities needed while a program runs. In local AI, it can also refer to a model execution engine.
Back to the textMoE — A model architecture that selects some of several expert subnetworks for each input. Total parameters can differ from the number activated for one token.
Back to the textTransformer — A neural-network architecture centered on attention, which computes relationships within an input. It is used in language as well as image, audio, and video models.
Back to the textAttention — A neural-network operation that calculates relationships between input tokens and combines information from each position into the current representation.
Back to the textKV cache — Memory that stores attention keys and values from earlier tokens for reuse during later token generation. Its size depends on context length and batch size.
Back to the textPrompt — The input text sent to a model. For generative models it describes the desired result and strongly shapes the output.
Back to the textSandbox — An isolated environment that restricts a program’s access to files, networks, and host capabilities. Its protection depends on mount, network, and execution-permission settings.
Back to the textAllowlist — A policy that permits only pre-approved targets, such as tools, commands, users, or network destinations.
Back to the text
Frequently asked questions
- What should you check first in this article?
- Flint is a mixture-of-experts model for coding agents published by Recursive in October 2026. It has 39.8B total parameters, about 2.5B active per token, and a 262,144-token context. Recursive reports 54.9% on Terminal-Bench 2.1, 89.7% on SWE-bench Pro v2 and 74.2% on SWE-bench Verified. Its official instructions assume a single B300 or H200 GPU, and Transformers modelling code is not included yet. Running it on a personal PC needs separately published GGUF weights and a llama.cpp-class runtime, whose performance may differ from the vendor figures.
- How much memory does it need?
- These instructions were not written with a personal PC in mind. B300 and H200 are data-centre GPUs whose memory configurations differ sharply from what an individual buys. On personal hardware you must use the separately published quantized GGUF, which runs on a different engine from the one the vendor measured.
- Where can you check the conditions and sources?
- The vendor reports 54.9% on Terminal-Bench 2.1, 89.7% on SWE-bench Pro v2 and 74.2% on SWE-bench Verified. The model card also states the evaluation conditions: temperature 1.0, top-p 0.95 and top-k 20, with Terminus 2 for Terminal-Bench and the mini-swe-agent harness for SWE-bench. Agentic scores average pass@1 over at least five attempts.