Goliath 120B
ModelPaidA large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge...
Capabilities5 decomposed
merged-model-instruction-following-with-dual-fine-tune-synthesis
Medium confidenceExecutes instruction-following tasks by leveraging a merged architecture combining two independently fine-tuned Llama 70B models (Xwin for competitive performance, Euryale for creative/uncensored outputs) into a single 120B parameter space. The merge framework preserves specialized capabilities from both source models while distributing computational load across the expanded parameter count, enabling nuanced responses that balance instruction adherence with creative flexibility without requiring separate model switching.
Synthesizes two independently fine-tuned Llama 70B models (Xwin optimized for competitive instruction-following, Euryale for creative/uncensored outputs) into a single 120B merged model using chargoddard's merge framework, distributing specialized capabilities across expanded parameter space rather than requiring separate model selection or ensemble inference
Offers larger parameter count (120B vs 70B base) with dual fine-tune synthesis for balanced instruction-following and creative flexibility in a single model, avoiding the latency and complexity of ensemble or model-switching approaches used by competitors
multi-turn-conversation-context-management
Medium confidenceMaintains coherent multi-turn dialogue by processing conversation history as sequential context within the model's token window, enabling the 120B merged model to track conversational state, user preferences, and prior statements across extended exchanges. The implementation relies on the underlying Llama architecture's attention mechanism to weight recent and salient context, with OpenRouter's API handling session management and context windowing to prevent token overflow while preserving semantic continuity.
Leverages the merged 120B model's expanded parameter capacity to maintain richer contextual representations across longer conversation histories compared to 70B base models, with dual fine-tune synthesis (Xwin + Euryale) potentially improving both instruction-following consistency and creative response variation within dialogue contexts
Larger parameter count enables deeper context retention than 70B competitors, though lacks explicit session persistence features found in some commercial chat APIs — requires client-side conversation management but avoids vendor lock-in to proprietary session stores
uncensored-creative-reasoning-with-fine-tune-blending
Medium confidenceGenerates creative, uncensored, and exploratory reasoning by blending the Euryale fine-tune (optimized for creative and unrestricted outputs) with Xwin's instruction-following precision through the merged model architecture. The dual fine-tune synthesis allows the model to produce creative content, roleplay scenarios, and exploratory reasoning without the safety guardrails typically present in standard instruction-tuned models, while maintaining coherence through Xwin's competitive instruction-following training.
Merges Euryale's uncensored creative fine-tuning with Xwin's competitive instruction-following in a single 120B model, enabling creative outputs without explicit refusal mechanisms while maintaining instruction coherence — a capability gap in standard instruction-tuned models that typically enforce safety constraints uniformly
Provides uncensored creative output in a single model without requiring separate 'jailbroken' model selection or prompt engineering workarounds, though lacks the safety guarantees and content filtering of mainstream models like GPT-4 or Claude
competitive-benchmark-instruction-following-via-xwin-synthesis
Medium confidenceAchieves competitive performance on instruction-following benchmarks (MMLU, MT-Bench, etc.) by incorporating Xwin fine-tuning into the merged 120B architecture, which was specifically optimized for high benchmark scores through reinforcement learning from human feedback (RLHF) and competitive instruction-tuning. The merge framework preserves Xwin's benchmark-optimized weights while expanding the parameter space, potentially improving generalization across diverse instruction-following tasks without sacrificing the specialized training that drives benchmark performance.
Incorporates Xwin's RLHF-optimized instruction-following training into a 120B merged model, leveraging expanded parameter capacity to potentially improve benchmark generalization while preserving the competitive instruction-tuning that drives Xwin's strong performance on MMLU, MT-Bench, and similar evaluations
Combines Xwin's benchmark-optimized instruction-following with 120B parameter scale for potentially superior generalization compared to 70B base models, though lacks published benchmark results to validate whether merge framework preserved or degraded Xwin's competitive performance
api-based-inference-with-openrouter-integration
Medium confidenceProvides access to the 120B merged model through OpenRouter's API infrastructure, handling model serving, load balancing, and request routing without requiring local deployment or GPU infrastructure. The integration abstracts away model hosting complexity, offering pay-per-token pricing and automatic failover across OpenRouter's provider network, while maintaining compatibility with standard LLM API patterns (messages format, streaming, token counting) that enable easy integration into existing applications.
Abstracts 120B model deployment through OpenRouter's multi-provider API infrastructure, enabling access to a computationally expensive merged model without local GPU requirements, with automatic load balancing and provider failover that would require significant engineering effort to replicate in self-hosted deployments
Eliminates infrastructure management overhead compared to self-hosted deployment, though introduces API latency and per-token costs that may exceed local inference for high-volume applications — trade-off between operational simplicity and cost/latency optimization
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with Goliath 120B, ranked by overlap. Discovered automatically through the match graph.
ReMM SLERP 13B
A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge
Qwen: Qwen3 Next 80B A3B Instruct
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Google: Gemma 4 26B A4B
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
TheDrummer: Skyfall 36B V2
Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.
Tencent: Hunyuan A13B Instruct
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
Neural Chat (7B)
Intel's Neural Chat — conversation-focused model
Best For
- ✓developers building uncensored AI assistants and creative applications
- ✓teams requiring high-parameter models with balanced instruction-following and creative capabilities
- ✓researchers experimenting with model merging techniques and multi-fine-tune synthesis
- ✓developers building chatbot and conversational AI applications
- ✓teams deploying customer support or interactive assistant systems
- ✓researchers studying context utilization and attention patterns in large merged models
- ✓creative writers and fiction authors using AI for brainstorming and content generation
- ✓developers building creative applications (games, interactive fiction, worldbuilding tools)
Known Limitations
- ⚠Merged model architecture may introduce subtle capability degradation in specialized domains where one source model excelled — no published ablation studies quantifying per-domain performance loss
- ⚠120B parameter count requires substantial VRAM (estimated 240GB+ for full precision inference), limiting deployment to enterprise-grade GPU clusters
- ⚠No published benchmarks isolating merged model performance vs. individual source models, making it difficult to assess whether merge framework preserved or degraded specific capabilities
- ⚠Merge framework details not fully documented — unclear how parameter conflicts between Xwin and Euryale fine-tuning objectives were resolved during synthesis
- ⚠Token window size limits total conversation length before context truncation — exact window size not specified in documentation, likely 4K-8K tokens based on Llama architecture
- ⚠No explicit control over context prioritization strategy — model uses learned attention weights rather than explicit recency or importance weighting
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Model Details
About
A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale. Credits to - [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge...
Categories
Alternatives to Goliath 120B
Are you the builder of Goliath 120B?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →