Open-weight model
qwen3.5-0.8b-medical-mlp5-first5
by Aditya G adityag-india/qwen3.5-0.8b-medical-mlp5-first5
qwen3.5-0.8b-medical-mlp5-first5 is an open-weight model from Aditya G, released under Apache License 2.0. It has 752M parameters and a 262,144-token context. At 16-bit it needs about 1.8 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Qwen/Qwen3.5-0.8B fully fine-tuned (no LoRA) on FreedomIntelligence/medical-o1-reasoning-SFT (en). Only the MLP blocks of layers [0, 1, 2, 3, 4] were trained; everything else is frozen. Checkpoint: best.pt. Split 80/10/10, 10 epochs, lr 1e-05.
Runs On
What it takes to serve qwen3.5-0.8b-medical-mlp5-first5 (752M 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 | 1.5 GB | 1.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.4 GB | 0.5 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 16, 2026.
qwen3.5-0.8b-medical-mlp5-first5 on every accelerator the SAVRN Index prices, at every precision
Model Card
By Aditya G, published under apache-2.0, revision 3cb7d602ae62.
Qwen/Qwen3.5-0.8B fully fine-tuned (no LoRA) on FreedomIntelligence/medical-o1-reasoning-SFT (en). Only the MLP blocks of layers [0, 1, 2, 3, 4] were trained; everything else is frozen. Checkpoint: best.pt. Split 80/10/10, 10 epochs, lr 1e-05.
Read Aditya G's full model card
exp1_mlp5_first5
Qwen/Qwen3.5-0.8B fully fine-tuned (no LoRA) on FreedomIntelligence/medical-o1-reasoning-SFT (en). Only the MLP blocks of layers [0, 1, 2, 3, 4] were trained; everything else is frozen. Checkpoint: best.pt. Split 80/10/10, 10 epochs, lr 1e-05.
Configuration
- Architecture
- Qwen3_5ForCausalLM
- Context length (tokens)
- 262,144
- Layers
- 24
- Hidden size
- 1,024
- Feed-forward size
- 3,584
- Attention heads
- 8
- Key/value heads
- 2
- Head dimension
- 256
- Vocabulary size
- 248,320
- Model type
- qwen3_5_text
Identity and Version
- Repository
- adityag-india/qwen3.5-0.8b-medical-mlp5-first5
- Publisher
- Aditya G
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 752M parameters
- Languages
- Not stated by the source
- Revision
- 3cb7d602ae62effeb2a4629fcab16b69cf83b9ad
- First published
- 2026-10-07
- Last updated
- 2026-10-07
Files and Weights
10 files, 1.5 GB in total. The weights are 1 file totalling 1.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.5 GB | 822c94206704 |
| config.json | Configuration | 1.8 KB | — |
| generation_config.json | Configuration | 116 B | — |
| train_config.yaml | Configuration | 517 B | — |
| README.md | Documentation | 380 B | — |
| chat_template.jinja | Other | 7.8 KB | — |
| loss_curve.png | Other | 83.9 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | a5cd9732badc |
| tokenizer_config.json | Tokenizer | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 1.5 GB
Released by Aditya G through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3.5-0.8B
- Trained on (disclosed) FreedomIntelligence/medical-o1-reasoning-SFT
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.5 GB |
| 16-bit | 1.5 GB |
| 8-bit | 0.8 GB |
| 4-bit | 0.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About qwen3.5-0.8b-medical-mlp5-first5
How much GPU memory does qwen3.5-0.8b-medical-mlp5-first5 need?
About 1.8 GB at 16-bit and 0.5 GB at 4-bit: the weights (752M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run qwen3.5-0.8b-medical-mlp5-first5 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.
Can I use qwen3.5-0.8b-medical-mlp5-first5 commercially?
Yes. qwen3.5-0.8b-medical-mlp5-first5 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
What is qwen3.5-0.8b-medical-mlp5-first5's context length?
262,144 tokens, from the maximum position embeddings in its published configuration.