LLM EXPLORER 59,358 MODELS INDEXED

Finch 8B by minnesotanlp

By minnesotanlp · 92 downloads
HF Repo ↗ Copy URL

Finch 8B is an open-source language model by minnesotanlp. Features: 8b LLM, VRAM: 16.4GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.25.

  Arxiv:2606.29082 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3-8b   Code-optimization   Conversational Dataset:minnesotanlp/finch-col...   Discovery   En   Endpoints compatible   Evolution-fine-tuning   Evolutionary-search   Mid-training   Mutation-operator   Qwen3   Region:us   Safetensors   Scientific-discovery
Model Card on HF 🤗: https://huggingface.co/minnesotanlp/Finch-8B 

Finch 8B Parameters and Internals

LLM NameFinch 8B
Repository 🤗https://huggingface.co/minnesotanlp/Finch-8B 
Base Model(s)  Qwen3 8B   Qwen/Qwen3-8B
Model Size8b
Required VRAM16.4 GB
Updated2026-08-08
Maintainerminnesotanlp
Model Typeqwen3
Model Files  16.4 GB
Supported Languagesen
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version5.2.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Finch 8B

Best Alternatives
Context / RAM
Downloads
Likes
PaCoRe 8B320K / 1.2 GB5448
RLVR 8B 0926320K / 1.2 GB638
...n3 8B 320K Context 10X Massive320K / 16.4 GB200
...r Of Horror Jan V1 256K Ctx 8B256K / 16.1 GB333
... BIG Jan Horror V1 256K Ctx 8B256K / 16.1 GB440
Qwen3 8B 256K Context 8X Grand256K / 16.4 GB950
...wen3 8B 192K Context 6X Larger192K / 16.4 GB550
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB17622931082
...Reason 8B Pretrain Competition128K / 16.8 GB2440
Marco DeepResearch 8B128K / 16.3 GB52027
Note: green Score (e.g. "73.2") means that the model is better than minnesotanlp/Finch-8B.