Like 359

Follow

Recursive Superintelligence, Inc. 262

Text Generation

Transformers

Safetensors

flint

conversational

License: apache-2.0

Model card Files Files and versions xet

Community 10

Deploy

Copy to bucket new

Use this model Instructions to use RecursiveSI/flint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers How to use RecursiveSI/flint with Transformers:

Use a pipeline as a high-level helper

from transformers import pipeline

pipe = pipeline("text-generation", model="RecursiveSI/flint") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)

pip install -U transformers accelerate

Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RecursiveSI/flint") model = AutoModelForCausalLM.from_pretrained("RecursiveSI/flint", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks

Google Colab

Kaggle

Local Apps Settings

vLLM How to use RecursiveSI/flint with vLLM:

Install vLLM from pip:

pip install vllm

Start the vLLM server:

vllm serve "RecursiveSI/flint"

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:8000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "RecursiveSI/flint", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Use Docker

docker model run hf.co/RecursiveSI/flint

SGLang How to use RecursiveSI/flint with SGLang:

Install SGLang from pip:

pip install sglang

Start the SGLang server:

python3 -m sglang.launch_server
--model-path "RecursiveSI/flint"
--host 0.0.0.0
--port 30000

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:30000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "RecursiveSI/flint", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Use Docker images

docker run --gpus all
--shm-size 32g
-p 30000:30000
-v ~/.cache/huggingface:/root/.cache/huggingface
--env "HF_TOKEN=<secret>"
--ipc=host
lmsysorg/sglang:latest
python3 -m sglang.launch_server
--model-path "RecursiveSI/flint"
--host 0.0.0.0
--port 30000

Call the server using curl (OpenAI-compatible API):

curl -X POST "http://localhost:30000/v1/chat/completions"
-H "Content-Type: application/json"
--data '{ "model": "RecursiveSI/flint", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Docker Model Runner How to use RecursiveSI/flint with Docker Model Runner:

docker model run hf.co/RecursiveSI/flint

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Evaluation

Model specifications

Getting started Recommended generation settings

Training

Limitations and responsible use

License and reporting

Blog | Hugging Face | Local engine | Documentation

Flint is Recursive’s mixture-of-experts language model for coding agents, with 39.8 billion total parameters and approximately 2.5 billion active per token. It is designed to investigate codebases, fix bugs, implement features, and write tests.

Flint supports text input and output, reasoning, and multi-turn tool use. In our release evaluations, it scores 54.9% on Terminal-Bench 2.1, 89.7% on SWE-bench Pro v2, and 74.2% on SWE-bench Verified.

This repository contains the BF16 checkpoint, model configuration, tokenizer, chat template, and an SGLang serving kit. Quantized variants are prepared separately for NVIDIA and Apple Silicon runtimes.

Flint results use temperature 1.0, top-p 0.95, and top-k 20. Terminal-Bench uses Terminus 2; SWE-bench uses mini-swe-agent. Agentic scores report average pass@1 over at least five attempts. † marks scores measured by Recursive; other comparison scores are developer-reported.

Evaluation setups vary across sources. Flint’s Terminal-Bench score counts solutions obtained through web retrieval as unsuccessful; developer-reported scores may not apply the same adjustment.

Model specifications

Property Flint

Developer Recursive

Architecture Decoder-only mixture-of-experts Transformer

Total parameters 39.8B

Active parameters per token Approximately 2.5B, including the output head¹

Layers 49: 2 dense layers followed by 47 MoE layers

Attention 35 sliding-window layers and 14 full-attention layers

Sliding window 513 tokens: the current token and 512 preceding tokens

Attention heads 32 query heads and 4 key/value heads; head dimension 128

Attention normalization Per-head QK RMSNorm and learned per-head attention sinks

Position encoding RoPE on sliding-window layers; no positional encoding on full-attention layers

Experts per MoE layer 256 routed experts, with 6 selected per token, plus an always-active shared expert

Documented context configuration 262,144 tokens, including prompt and generated output

Vocabulary 150,144 tokens

Input / output Text / text

Stated knowledge cutoff June 2026

¹ The active-parameter convention includes the output head and excludes the full input embedding matrix. The active body alone is approximately 2.2B parameters. “40B-A2.5B” is the rounded model-size designation.

Getting started

Flint runs on one B300 or H200 GPU per replica with the SGLang kit in sglang/. Transformers modeling code is not included yet.

pip install -U huggingface_hub openai hf download RecursiveSI/flint --local-dir flint && cd flint # about 80 GB docker build -t flint-sglang sglang docker run -d --name flint --gpus '"device=0"' --ipc=host -p 127.0.0.1:30000:30000
-v "$PWD:/model" -e MODEL=/model flint-sglang bash /model/sglang/serve_b300.sh # H200: serve_h200.sh until curl -sf localhost:30000/health_generate >/dev/null; do sleep 15; done # progress: docker logs -f flint python3 sglang/example_client.py --base-url http://localhost:30000/v1 # reasoning and a tool call

from openai import OpenAI

client = OpenAI(base_url="http://localhost:30000/v1", api_key="unused") response = client.chat.completions.create( model="flint", messages=[{"role": "user", "content": "Write a Python function that merges overlapping intervals."}], max_tokens=32768, ) print(response.choices[0].message.content)

sglang/README.md covers requirements, serve-script options, multi-GPU deployments, and API details.

Recommended generation settings

Setting Value

Temperature 1.0

Top-p / top-k 0.95 / 20

Output budget for hard problems At least 32768 tokens, including reasoning

The server applies these sampling settings when a request omits them. Flint supports OpenAI-compatible tool calls. Use the checkpoint’s chat template and preserve returned reasoning_content in conversation history. Prompt and output share the context window.

Training

Flint was trained from scratch through pretraining, mid-training, supervised fine-tuning, and reinforcement learning. Training includes text and code, instruction following, and agentic tasks.

Limitations and responsible use

Flint’s supervised fine-tuning included safety-oriented examples, but the model can still produce incorrect or harmful content, faulty code, or inappropriate tool calls. Test generated code and review consequential changes before applying them. Tool-using applications should enforce their own permissions and execution boundaries; structured tool-call grammar does not prevent the model from choosing an unsafe or incorrect action.

Long reasoning can increase latency and exhaust the output budget before an answer is complete. The context configuration is a capacity limit, not a guarantee of uniform accuracy across all sequence lengths or tasks. Results can vary with checkpoint precision and inference runtime; evaluate the specific checkpoint and runtime you intend to deploy.

License and reporting

Flint is released under the Apache 2.0 license. Hosted API terms and data practices are separate from the weight license.

For model and serving issues, contact support@recursive.com and include the checkpoint revision, runtime version, hardware, launch command, and a minimal reproduction. Report safety concerns or suspected misuse to safety@recursive.com, and security vulnerabilities to security@recursive.com.

","eos_token":"<|end_of_text|>"},"chat_template_jinja":"{%- macro flint_text(t) -%}\n{%- if t is string -%}\n{{- t | replace("\x00", "") | replace("<think>", "") | replace("</think>", "") | replace("<|begin_of_text|>", "<|begin_of_text|>") | replace("<|end_of_text|>", "<|end_of_text|>") | replace("<|system|>", "<|system|>") | replace("<|developer|>", "<|developer|>") | replace("<|user|>", "<|user|>") | replace("<|assistant|>", "<|assistant|>") | replace("<|observation|>", "<|observation|>") -}}\n{%- else -%}\n{{- t -}}\n{%- endif -%}\n{%- endmacro -%}\n{%- set tool_preamble -%}\n{%- if tools %}<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{%- for tool in tools %}\n{%- set fn = tool.function if tool.function is defined else tool %}\n{{ fn | tojson(ensure_ascii=False) }}\n{%- endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value>...</tool_call>\n{% endif -%}\n{%- endset -%}\n{%- set ns = namespace(tools_pending=true) -%}\n{%- for m in messages -%}\n{%- if ns.tools_pending and m.role != 'system' -%}\n{{ tool_preamble }}\n{%- set ns.tools_pending = false -%}\n{%- endif -%}\n{%- if m.role == 'system' -%}\n<|system|>{{ flint_text(m.content) }}\n{%- elif m.role == 'developer' -%}\n<|developer|>{{ flint_text(m.content) }}\n{%- elif m.role == 'user' -%}\n<|user|>{{ flint_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- if m.reasoning_content %}<think>{{ m.reasoning_content }}</think>{% endif -%}\n{%- if m.content %}{{ m.content }}{% endif -%}\n{%- if m.tool_calls -%}\n{%- for tc in m.tool_calls -%}\n{%- set fn = tc.function if tc.function is defined else tc -%}\n<tool_call>{{ fn.name }}\n{%- for k, v in fn.arguments.items() -%}\n<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>\n{%- endfor -%}\n</tool_call>\n{%- endfor -%}\n{%- endif -%}\n{%- elif m.role == 'tool' -%}\n<|observation|><tool_response>{{ flint_text(m.content) }}</tool_response>\n{%- endif -%}\n{%- endfor -%}\n{%- if ns.tools_pending -%}\n{{ tool_preamble }}\n{%- endif -%}\n{%- if add_generation_prompt -%}\n<|assistant|>\n{%- endif -%}\n"},"createdAt":"2026-10-21T14:20:58.000Z","discussionsDisabled":false,"discussionsSorting":"recently-created","downloads":420,"downloadsAllTime":420,"id":"RecursiveSI/flint","isLikedByUser":false,"availableInferenceProviders":[],"showHuggingChatEntry":false,"inference":"","lastModified":"2026-10-21T14:24:03.000Z","likes":359,"pipeline_tag":"text-generation","library_name":"transformers","librariesOther":[],"trackDownloads":true,"model-index":null,"private":false,"repoType":"model","gated":false,"tags":["transformers","safetensors","flint","text-generation","conversational","license:apache-2.0","endpoints_compatible","region:us"],"tag_objs":[{"id":"text-generation","label":"Text Generation","type":"pipeline_tag","subType":"nlp"},{"id":"transformers","label":"Transformers","type":"library"},{"id":"s