Open-weight model
sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800
by Sagnik Mukherjee sagnikM/sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800
sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800 is an open-weight model from Sagnik Mukherjee. It has 952M parameters and a 32,768-token context. At 16-bit it needs about 2.3 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 sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800 (952M 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 | 1.9 GB | 2.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.0 GB | 1.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.5 GB | 0.6 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.
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
- RoPE base
- 1e+06
- Model type
- qwen2
Identity and Version
- Repository
- sagnikM/sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800
- Publisher
- Sagnik Mukherjee
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 952M parameters
- Languages
- Not stated by the source
- Revision
- f4619e2e2754b0c59da356877abc4c6523df7bf3
- First published
- 2026-09-25
- Last updated
- 2026-09-25
Files and Weights
18 files, 30.5 GB in total. The weights are 7 files totalling 30.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00007.safetensors | Weights | 5.0 GB | f67f5c224ad3 |
| model-00002-of-00007.safetensors | Weights | 4.8 GB | fdeb9333de1c |
| model-00003-of-00007.safetensors | Weights | 4.9 GB | 5089f8a213d9 |
| model-00004-of-00007.safetensors | Weights | 4.9 GB | 46e97c193848 |
| model-00005-of-00007.safetensors | Weights | 5.0 GB | 45a562437181 |
| model-00006-of-00007.safetensors | Weights | 3.7 GB | 935ac519558d |
| model-00007-of-00007.safetensors | Weights | 2.2 GB | dc4f2423233d |
| added_tokens.json | Configuration | 605 B | — |
| config.json | Configuration | 1.3 KB | — |
| generation_config.json | Configuration | 217 B | — |
| model.safetensors.index.json | Configuration | 27.8 KB | — |
| special_tokens_map.json | Configuration | 613 B | — |
| chat_template.jinja | Other | 2.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | ec2d256feefa |
| tokenizer_config.json | Tokenizer | 4.7 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 30.5 GB
Released by Sagnik Mukherjee through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 30.5 GB |
| 16-bit | 1.9 GB |
| 8-bit | 1.0 GB |
| 4-bit | 0.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800
How much GPU memory does sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800 need?
About 2.3 GB at 16-bit and 0.6 GB at 4-bit: the weights (952M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800 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 sdft-biology-qwen25-7b-lr1e-5-response2048-seed42-step1800's context length?
32,768 tokens, from the maximum position embeddings in its published configuration.