70.55B Llama merge
The captured configuration reports LlamaForCausalLM with 70,553,706,496 parameters, tagged as a mergekit merge.
Open Source Model Profile · Nohobby
L3.3-Prikol-70B-v0.5
L3.3-Prikol-70B-v0.5 is a 70.55B-parameter Llama text-generation merge from Nohobby. Hub tags mark it as a mergekit merge with conversational support.
- Publisher
- Nohobby
- Task
- text-generation
- Model type
- llama
- License
- Unknown
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
L3.3-Prikol-70B-v0.5 is published by Nohobby as a Llama text-generation merge. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 70,553,706,496 parameters. Hub tags mark it as a mergekit merge with conversational support, and according to the model card the publisher specifies Llama3 prompt format.
Recorded capabilities
Llama3 prompt and samplers
According to the model card, the publisher specifies Llama3 prompt format with 1.15 temp and 0.015 minP samplers.
Multi-source mergekit recipe
Hub tags and the model card document a multi-step mergekit recipe across many 70B sources, including Euryale, Cirrus, Anubis, and Euryale-family inputs.
Documented quant variants
According to the model card, the publisher notes GGUF Imatrix and Static plus exl2 4.0bpw and 6.0bpw quant references.
Use cases in the source record
- Conversational text-generation experiments using the documented Llama3 prompt format.
- Merge-analysis workflows comparing the tagged 70B merge sources and the card-documented mergekit steps.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No license value was captured, so reuse terms are unknown from this record.
- No context-window value was extracted.
- Parts of the model card are informal publisher notes rather than structured training documentation.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: Nohobby/L3.3-Prikol-70B-v0.5
Captured: Unknown. Processed: 2026-09-07T19:35:14.448214+00:00.
Prikol I don't even know anymore Overview 99% of mergekit addicts quit before they hit it big. Gosh, I need to create an org for my test runs - my profile looks like a dumpster. What was it again? Ah, the new model. Exactly what I wanted. All I had to do was yank out the cursed official DeepSeek distill and here we are. From the brief tests it gave me some unusual takes on the character cards I'm used to. Just this makes it worth it imo. Also the writing is kinda nice. Settings: Prompt format: Llama3 Samplers: 1.15 temp, 0.015 minP (by @Geechan) Quants GGUF: Imatrix | Static exl2: 4.0bpw | 6.0bpw Merge Details There's a ridiculous a…
F001F002F003F004F005F006F007F008F009F010F011F012F013F014F015F022