GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Nayrosk
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Nayrosk
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
sh
ollama run hf.co/nayrosk/rust-errors-qwen3-4b:Q4_K_Mllama-cli -hf nayrosk/rust-errors-qwen3-4b:Q4_K_Moverbrainer wrote questions on the topics below with the generator model, kept the parent model's answers, then fine-tuned the base model on them with Axolotl. The parent's reasoning was left out of training on purpose (chat_template = "chatml"): a run that also trained the reasoning made a 1.7B child think until it hit its token limit.
| Parent model | deepseek/deepseek-v4-pro:thinking |
| Generator model | deepseek/deepseek-v4-flash |
| Base model | Qwen/Qwen3-4B |
| Adapter | QLoRA |
| Examples | 1746 train, 194 eval |
| Epochs | 3 |
| Learning rate | 0.0002 |
| Sequence length | 4096 |
| Final loss | 1.04 train, 1.10 eval |
| Training time | 1 h 18 min |
Topics:
Trained on Runpod (NVIDIA A40) for about $0.81.
Against the parent on 194 held-out questions, judged pairwise by a local qwen3.5:9b: the child wins or ties on 20.2% of them, with a p50 latency of 5.6 s on one RTX A5000, at about 6% of the parent's cost per request. It is a cheap first line, not a replacement for the parent on hard questions. The full case study, with a 1.7B comparison and its limits, is in the overbrainer repository (examples/rust-errors).
sh
cargo install --locked overbrainerWith these sections of overbrainer.toml (project, providers, targets and keys left out), then overbrainer run:
toml
[[topics]]name = "borrow_checker"description = "Rust borrow checker errors (E0499, E0502, E0505, E0506): what triggers each one and how to fix the code"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "moves"description = "Rust use-after-move and move-out-of-borrow errors (E0382, E0507, E0508): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "lifetimes"description = "Rust lifetime errors (E0106, E0597, E0716, E0621, lifetime may not live long enough): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "traits"description = "Rust trait bound and method resolution errors (E0277, E0599, E0038 object safety): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "types"description = "Rust type mismatch and inference errors (E0308, E0282, E0283): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "mutability"description = "Rust mutability errors (E0596, E0594, E0384) and interior mutability: causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "generics"description = "Rust generics and associated type errors (E0107, E0191, E0220, E0207): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "async_send"description = "Rust async errors: futures that are not Send, holding guards across await, missing async runtime: causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "modules"description = "Rust visibility, import and module errors (E0603, E0432, E0433, E0425): causes and fixes"subtopics = 4questions_per_subtopic = 55 [roles.generator]provider = "nanogpt"model = "deepseek/deepseek-v4-flash"reasoning = falsemax_tokens = 16384 [roles.parent]provider = "nanogpt"model = "deepseek/deepseek-v4-pro:thinking"reasoning = truemax_tokens = 16384 [roles.judge]provider = "xana"model = "qwen3.5:9b"reasoning = falsemax_tokens = 1024reasoning_effort = "none" [training]base_model = "Qwen/Qwen3-4B"adapter = "qlora"epochs = 3learning_rate = 0.0002lora_r = 16lora_alpha = 32lora_dropout = 0.05sequence_len = 4096micro_batch_size = 2gradient_accumulation_steps = 4optimizer = "adamw_torch_fused"lr_scheduler = "cosine"sample_packing = trueevals_per_epoch = 4saves_per_epoch = 1merge = false [training.axolotl_extra]chat_template = "chatml" [pipeline]concurrency = 2max_retries = 5dedup_threshold = 0.8eval_ratio = 0.1seed = 42include_system_prompt = falseembedding_threshold = 0.9question_batch_size = 10request_timeout_secs = 600See the overbrainer docs.
overbrainer distills a big LLM into a small one from your terminal. If this model is useful, a star on GitHub helps.
ollama run hf.co/nayrosk/rust-errors-qwen3-4b:Q4_K_Mllama-cli -hf nayrosk/rust-errors-qwen3-4b:Q4_K_Mcargo install --locked overbrainer[[topics]]name = "borrow_checker"description = "Rust borrow checker errors (E0499, E0502, E0505, E0506): what triggers each one and how to fix the code"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "moves"description = "Rust use-after-move and move-out-of-borrow errors (E0382, E0507, E0508): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "lifetimes"description = "Rust lifetime errors (E0106, E0597, E0716, E0621, lifetime may not live long enough): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "traits"description = "Rust trait bound and method resolution errors (E0277, E0599, E0038 object safety): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "types"description = "Rust type mismatch and inference errors (E0308, E0282, E0283): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "mutability"description = "Rust mutability errors (E0596, E0594, E0384) and interior mutability: causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "generics"description = "Rust generics and associated type errors (E0107, E0191, E0220, E0207): causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "async_send"description = "Rust async errors: futures that are not Send, holding guards across await, missing async runtime: causes and fixes"subtopics = 4questions_per_subtopic = 55 [[topics]]name = "modules"description = "Rust visibility, import and module errors (E0603, E0432, E0433, E0425): causes and fixes"subtopics = 4questions_per_subtopic = 55 [roles.generator]provider = "nanogpt"model = "deepseek/deepseek-v4-flash"reasoning = falsemax_tokens = 16384 [roles.parent]provider = "nanogpt"model = "deepseek/deepseek-v4-pro:thinking"reasoning = truemax_tokens = 16384 [roles.judge]provider = "xana"model = "qwen3.5:9b"reasoning = falsemax_tokens = 1024reasoning_effort = "none" [training]base_model = "Qwen/Qwen3-4B"adapter = "qlora"epochs = 3learning_rate = 0.0002lora_r = 16lora_alpha = 32lora_dropout = 0.05sequence_len = 4096micro_batch_size = 2gradient_accumulation_steps = 4optimizer = "adamw_torch_fused"lr_scheduler = "cosine"sample_packing = trueevals_per_epoch = 4saves_per_epoch = 1merge = false [training.axolotl_extra]chat_template = "chatml" [pipeline]concurrency = 2max_retries = 5dedup_threshold = 0.8eval_ratio = 0.1seed = 42include_system_prompt = falseembedding_threshold = 0.9question_batch_size = 10request_timeout_secs = 600