A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
iOS chat model: grounded ThoxChat configuration (not training) over Qwen2.5-3B-Instruct. 11.32 tok/s (measured 2026-10-31). Mobile GGUF target. Not device-qualified. Apache-2.0.
ThoxMini (4 GB) target chat configuration over Qwen2.5-3B-Instruct (THOX configuration, not training). 11.66 tok/s (measured 2026-10-31). Distinct from trained ThoxMini-Phi4Mini. Apache-2.0.
ThoxClip (6 GB) target chat configuration over Qwen2.5-3B-Instruct (THOX configuration, not training). 11.03 tok/s (measured 2026-10-31). Distinct from trained ThoxClip-Qwen3-0.6B. Apache-2.0.
Fine-tuned Pokédex model based on Qwen 2.5 3B.
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
Nex-N2.5-mini (nex-agi) : MoE 35B / ~3B actifs post-trained on Qwen3.5-35B-A3B. Vision, tool-calling, reasoning, 256k context. Quants Q5_K_M, Q4_K_M (latest), Q3_K_M, Q2_K.
TNEA-Advisor is a hyper-localized, data-driven admissions strategist mathematically fused into Qwen 2.5 3B and quantized to 4-bit GGUF for consumer hardware. It bypasses cloud dependencies to deliver hyper-accurate, offline engineering cutoff predictions.
Base model
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model. I-Quants models, abliterated with uncensored prompt.
Cluster coding model: THOX configuration (not training) of Qwen2.5-Coder-32B-Instruct for local software engineering and MeshStack deployments; 92 languages per the base record. Apache-2.0.
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model. I-Quants models.
Text-only Nemotron 3.5 Bolt E4B GGUF files, thinking off as measured. Default: q3_k_xl. TurinTech models, built with Artemis. Measured Q3_K_XL: Mean KLD 0.0414, Same top p 92.98% vs BF16 on held-out OASST1 chat; protocol rtx3060-heldout-2026-10-28.
llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF with Vision
THOX-trained LoRA (rank 32) on Qwen2.5-0.5B-Instruct, THOX-authored corpus of 982 examples. GATE49 47/49 (development set); grounding required at runtime. Apache-2.0.
Typhoon2.5 30B A3B - 30B parameters with 3B active Thai / English bilingual LLM build based on Qwen3.
32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data with performance on par with o1 preview.
Llama 3.1 8B Instruct trained on 9,000,000 Claude Opus/Sonnet tokens
fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the OpenThoughts-114k dataset, available in [F16, q8_0, q6_K, q4_K_S]