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
Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2
by Brandon Howe BrandonHowe/Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2
Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2 is an open-weight model for text generation from Brandon Howe. It has 8.2B parameters and a 32,768-token context. At 16-bit it needs about 19.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Standalone merged BF16 model from epoch 2.0, step 756. Dataset: CompassioninMachineLearning/urban12738cleaned at ef7c0e742df63ea319e35d02d9f6ba63d6e7c68d.
Parameters8.2B
Context32,768
Weights16.4 GB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2 (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 Oct 23, 2026.
Model Card
Standalone merged BF16 model from epoch 2.0, step 756. Dataset: CompassioninMachineLearning/urban12738cleaned at ef7c0e742df63ea319e35d02d9f6ba63d6e7c68d. Training: 10,072 distinct documents plus 2,000 repeat exposures per epoch; 200 disjoint validation documents. Merged with Unsloth's native savepretrainedmerged(savemethod="merged16bit"). Weights are validated BF16 and packaged losslessly into eight safetensors shards. No adapter is required to load this model. See runmanifest.json for base revision, document selection hashes, training parameters and export validation. Training does not establish an improvement in compassion; evaluate that separately.
Excerpt from the card by Brandon Howe.
Configuration
- Architecture
- Qwen3ForCausalLM
- Context length (tokens)
- 32,768
- 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
- BrandonHowe/Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2
- Publisher
- Brandon Howe
- Task
- Text generation
- Modality
- Text
- Library
- transformers
- Parameters
- 8.2B parameters
- Languages
- Not stated by the source
- Revision
- 9ee1a6f96c8b73195bab87dda88dd21310d0029b
- First published
- 2026-10-11
- Last updated
- 2026-10-11
Files and Weights
22 files, 16.4 GB in total. The weights are 8 files totalling 16.4 GB in safetensors.
Weights8 files · 16.4 GB
Configuration7 files · 46.1 KB
Tokenizer4 files · 15.9 MB
Documentation1 file · 939 B
Other1 file · 4.1 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00008.safetensors | Weights | 2.2 GB | 7fb400cc9e12 |
| model-00002-of-00008.safetensors | Weights | 2.2 GB | d21f581c2ab0 |
| model-00003-of-00008.safetensors | Weights | 2.1 GB | 49677d05377d |
| model-00004-of-00008.safetensors | Weights | 2.2 GB | f5ba96e35c3b |
| model-00005-of-00008.safetensors | Weights | 2.2 GB | 3529b056820f |
| model-00006-of-00008.safetensors | Weights | 2.1 GB | 9bb07dc8c097 |
| model-00007-of-00008.safetensors | Weights | 2.1 GB | 2c8bc7ce416d |
| model-00008-of-00008.safetensors | Weights | 1.2 GB | 37b9339177c0 |
| added_tokens.json | Configuration | 707 B | — |
| config.json | Configuration | 1.5 KB | — |
| export_validation.json | Configuration | 470 B | — |
| generation_config.json | Configuration | 150 B | — |
| model.safetensors.index.json | Configuration | 32.9 KB | — |
| run_manifest.json | Configuration | 9.8 KB | — |
| special_tokens_map.json | Configuration | 503 B | — |
| README.md | Documentation | 939 B | — |
| chat_template.jinja | Other | 4.1 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
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 16.4 GB
Download from Brandon Howe
Released by Brandon Howe through its official repository on Hugging Face.
Built From
- Derived from Qwen/Qwen3-8B-Base
- Trained on (disclosed) CompassioninMachineLearning/urban_12738_cleaned
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 16.4 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 Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2
How much GPU memory does Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2 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 Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2 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 is Qwen3-8b-urban-seed1-20261010-nvl-koqf8weu-CPT-merged-epoch-2's context length?
32,768 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…
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…
English | 简体中文 Qwen3-8B-CC-SFT-v2 is a failure-targeted continued-SFT checkpoint designed to improve coding-agent state preservation and continuation across Claude Code native context compaction. It is initialized from Qwen3-8B-CC-SFT-v1 and trained on compact-aware, context-correct supervision distilled from GLM-5.3 under real Claude Code native compaction. Best observed canonical303 Pass@1: 52.48% (159/303) — 4090 run of this same checkpoint at T=0.5 (temperature selected on an independent dev set; see the table below). Best observed configurations of this same checkpoint: - T=0.5 was selected on an independent 60-task development set (task-id and repo disjoint from canonical303), then…
Ido Levy 1,2 · 1,2 The trained questioner from Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents, with its LoRA adapter merged into Qwen3-8B. It is a standard full-weight model: it loads without PEFT and serves with vLLM, SGLang or TGI like any Qwen3-8B. - The adapter, with the results, the training details, the limitations and a complete two-turn - Quantized for llama.cpp, Ollama and LM Studio: This is training seed 1, the adapter at the root of the adapter repository. The merge ran in float32 and the weights are stored in bfloat16. On the adapter card's two-turn example, greedy decoding with this model returns the adapter's output character for character.…