Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…
Open-weight model · Text generation
Symbiotic-8B
by Convergent Intelligence reaperdoesntknow/Symbiotic-8B
Purpose: Long-memory symbolic reasoning + high-fidelity language generation SymbioticLM-8B is a state-of-the-art hybrid transformer model with built-in symbolic cognition.
Parameters8.2B
Context40,960
Weights43.0 GB
Licenseafl-3.0
AccessOpen weights
Monthly Downloads4.5k
Runs On
What it takes to serve Symbiotic-8B (8.2B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 16.4 GB | 19.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 8.2 GB | 9.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.1 GB | 4.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
By Convergent Intelligence, published under afl-3.0, revision d3a0eef9fb18.
Purpose: Long-memory symbolic reasoning + high-fidelity language generation SymbioticLM-8B is a state-of-the-art hybrid transformer model with built-in symbolic cognition. It combines an 8B Qwen-based transformer with modular symbolic processors and a persistent memory buffer. The model supports both general conversation and deep symbolic tasks such as theorem generation, logical chaining, and structured reasoning with retained memory across turns. - General symbolic reasoning and logical conversation - Code + math proof modeling - Not instruction-tuned (e.g., chat-style inputs may require prompt engineering) - Larger memory buffer may increase CPU load slightly - Symbolic inference is…
Read Convergent Intelligence's full model card
SymbioticLM-8B
Model Type: Hybrid Symbolic–Transformer
Base Model: Qwen-8B
Framework: PyTorch + Transformers-compatible
Purpose: Long-memory symbolic reasoning + high-fidelity language generation
Overview
SymbioticLM-8B is a state-of-the-art hybrid transformer model with built-in symbolic cognition. It combines an 8B Qwen-based transformer with modular symbolic processors and a persistent memory buffer. The model supports both general conversation and deep symbolic tasks such as theorem generation, logical chaining, and structured reasoning with retained memory across turns.
Architecture Highlights
- Backbone: Qwen-8B rotary transformer
- Symbolic Dim: 4096
- Symbolic Modules:
- ThoughtDynamicsLNN (multi-head LSTM attention)
- CrystallineProcessor (DNAConv GNN)
- LiquidThoughtProcessor (recurrent symbol folding)
- HelicalDNAProcessor (helical linear projection)
- Memory: 2048 symbolic vectors (float32) with entropy-aware retrieval and contextual recall
- Dream Mode: Self-generates symbolic cognition offline
Files Included
| File | Description |
|---|---|
model.bin |
PyTorch weights (LFS tracked) |
model.safetensors |
Same weights in safetensors format (recommended) |
memory.pt |
Symbolic memory snapshot (entropic, pretrained) |
config.json |
Base model configuration |
generation_config.json |
Sampling and decoding config (temperature, top_p, etc.) |
tokenizer.json |
Tokenizer data with custom tags and structure |
added_tokens.json |
Extra tokens like <THM>, <PROOF>, <D_EPS> |
special_tokens_map.json |
Maps for special tokens used during generation |
Intended Uses
- General symbolic reasoning and logical conversation
- Memory-aware tutoring, research assistants
- Code + math proof modeling
- Context-persistent dialogue systems
Limitations
- Not instruction-tuned (e.g., chat-style inputs may require prompt engineering)
- Larger memory buffer may increase CPU load slightly
- Symbolic inference is offline-evolved; memory must be actively seeded
Discrepancy Calculus Foundation
This model is part of the Convergent Intelligence LLC: Research Division portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model should produce and what it actually produces.
DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as structural signals that reveal the geometry of the learning problem. Key concepts:
- Discrepancy Operator (D): Measures the gap between expected and observed behavior at each training step
- Jump Sets: Boundaries where model behavior changes discontinuously — these are features, not bugs
- Ghost Imprinting: Teacher knowledge that transfers to student models through weight-space topology rather than explicit distillation signal
For the full mathematical treatment, see Discrepancy Calculus: Foundations and Core Theory (DOI: 10.57967/hf/8194).
Citation chain: Structure Over Scale (DOI: 10.57967/hf/8165) → Three Teachers to Dual Cognition (DOI: 10.57967/hf/8184) → Discrepancy Calculus (DOI: 10.57967/hf/8194)
Citations
This model was designed and built from Discrepancy Analysis, paper to be published soon!
Convergent Intelligence Portfolio
Part of the Symbiotic AI Series by Convergent Intelligence LLC: Research Division
Related Models
| Model | Downloads | Format |
|---|---|---|
| Symbiotic-1B | 4 | HF |
| Symiotic-14B | 3 | HF |
| Symbiotic-Beta | 3 | HF |
Top Models from Our Lab
Total Portfolio: 41 models | 2,781 total downloads
Last updated: 2026-03-28 12:57 UTC
From the Convergent Intelligence Portfolio
DistilQwen Collection — Our only BF16 series. Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B on H100. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. The rest of the portfolio proves structure beats scale on CPU. This collection shows what happens when you give the methodology real hardware.
Top model: Qwen3-1.7B-Coder-Distilled-SFT — 508 downloads
Full methodology: Structure Over Scale (DOI: 10.57967/hf/8165)
Convergent Intelligence LLC: Research Division
Configuration
- Architecture
- Qwen3ForCausalLM
- Context length (tokens)
- 40,960
- Layers
- 36
- Hidden size
- 4,096
- Feed-forward size
- 12,288
- Attention heads
- 32
- Key/value heads
- 8
- Head dimension
- 128
- Vocabulary size
- 151,936
- RoPE base
- 1,000,000
- Stored precision
- bfloat16
- Model type
- qwen3
Identity and Version
- Repository
- reaperdoesntknow/Symbiotic-8B
- Publisher
- Convergent Intelligence
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 8.2B parameters
- Languages
- en
- Revision
- d3a0eef9fb185fdcebdc9e61d6a52064dc52be7d
- First published
- 2025-05-06
- Last updated
- 2026-09-18
Files and Weights
19 files, 43.1 GB in total. The weights are 8 files totalling 43.0 GB in bin, safetensors.
Weights8 files · 43.0 GB
Configuration5 files · 36.9 KB
Tokenizer4 files · 15.9 MB
Documentation1 file · 6.5 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00007.safetensors | Weights | 5.0 GB | ef9b808bfd5c |
| model-00002-of-00007.safetensors | Weights | 4.8 GB | 16dc83b78630 |
| model-00003-of-00007.safetensors | Weights | 4.8 GB | dd4ed71c9a98 |
| model-00004-of-00007.safetensors | Weights | 5.0 GB | 9d0d4a0e3852 |
| model-00005-of-00007.safetensors | Weights | 4.8 GB | 9a1256a3c728 |
| model-00006-of-00007.safetensors | Weights | 4.8 GB | ecbff6633142 |
| model-00007-of-00007.safetensors | Weights | 3.5 GB | a73aac17dc52 |
| model.bin | Weights | 10.3 GB | f6cb74dc6bfb |
| added_tokens.json | Configuration | 707 B | — |
| config.json | Configuration | 769 B | — |
| generation_config.json | Configuration | 1.9 KB | — |
| model.safetensors.index.json | Configuration | 32.9 KB | — |
| special_tokens_map.json | Configuration | 613 B | — |
| README.md | Documentation | 6.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| tokenizer_config.json | Tokenizer | 9.7 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- afl-3.0
- Access
- Open weights, no gate
- Download size
- 43.0 GB
Download from Convergent Intelligence
Released by Convergent Intelligence through its official repository on Hugging Face.
Built From
- Derived from Qwen/Qwen3-8B
- Trained on (disclosed) 0xZee/dataset-CoT-Advanced-Calculus-268
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 43.0 GB |
| 16-bit | 16.4 GB |
| 8-bit | 8.2 GB |
| 4-bit | 4.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Symbiotic-8B
How much GPU memory does Symbiotic-8B need?
About 19.7 GB at 16-bit and 4.9 GB at 4-bit: the weights (8.2B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Symbiotic-8B on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
What license is Symbiotic-8B released under?
afl-3.0, as its publisher declares it. Read the license text before commercial use.
What is Symbiotic-8B's context length?
40,960 tokens, from the maximum position embeddings in its published configuration.
Similar Models
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…
The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of leading models, such as O3 and Gemini 2.5 Pro. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning…
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features: - Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios. - Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and…
The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks. Model Architecture: Llama 3.1 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.…
Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. Model developers Meta Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants. Input Models input text only. Output Models generate text and code only. Model Architecture Llama 3 is an auto-regressive language…