Open-weight model
socratic_qwen8b-dpo-merged
by Shekhar Lamichhane Magar Susu11/socratic_qwen8b-dpo-merged
socratic_qwen8b-dpo-merged is an open-weight model from Shekhar Lamichhane Magar. It has 7.6B parameters and a 32,768-token context. At 16-bit it needs about 18.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve socratic_qwen8b-dpo-merged (7.6B 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 | 15.2 GB | 18.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 7.6 GB | 9.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 3.8 GB | 4.6 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 18, 2026.
socratic_qwen8b-dpo-merged on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Qwen2ForCausalLM
- Context length (tokens)
- 32,768
- Layers
- 28
- Hidden size
- 3,584
- Feed-forward size
- 18,944
- Attention heads
- 28
- Key/value heads
- 4
- Vocabulary size
- 152,064
- Model type
- qwen2
Identity and Version
- Repository
- Susu11/socratic_qwen8b-dpo-merged
- Publisher
- Shekhar Lamichhane Magar
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 7.6B parameters
- Languages
- Not stated by the source
- Revision
- 2c8324bc22828a5bc2df33884ff804172b1aa639
- First published
- 2026-09-28
- Last updated
- 2026-09-28
Files and Weights
7 files, 15.2 GB in total. The weights are 1 file totalling 15.2 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 15.2 GB | 58cf1f5c8821 |
| config.json | Configuration | 1.4 KB | — |
| generation_config.json | Configuration | 242 B | — |
| chat_template.jinja | Other | 2.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| tokenizer_config.json | Tokenizer | 665 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 15.2 GB
Released by Shekhar Lamichhane Magar through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 15.2 GB |
| 16-bit | 15.2 GB |
| 8-bit | 7.6 GB |
| 4-bit | 3.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About socratic_qwen8b-dpo-merged
How much GPU memory does socratic_qwen8b-dpo-merged need?
About 18.3 GB at 16-bit and 4.6 GB at 4-bit: the weights (7.6B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run socratic_qwen8b-dpo-merged 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 socratic_qwen8b-dpo-merged's context length?
32,768 tokens, from the maximum position embeddings in its published configuration.