Open-weight model
DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16
by MAXLABS maxlabs-ai/DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16
DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16 is an open-weight model from MAXLABS. It has 8B parameters and a 131,072-token context. At 16-bit it needs about 19.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
This model was quantized using oQ (oMLX v0.7.0rc1) mixed-precision quantization.
Runs On
What it takes to serve DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16 (8B 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 | 16.1 GB | 19.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 8.0 GB | 9.6 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 4.0 GB | 4.8 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
This model was quantized using oQ (oMLX v0.7.0rc1) mixed-precision quantization.
Excerpt from the card by MAXLABS.
Configuration
- Architecture
- LlamaForCausalLM
- Context length (tokens)
- 131,072
- Layers
- 32
- Hidden size
- 4,096
- Feed-forward size
- 14,336
- Attention heads
- 32
- Key/value heads
- 8
- Vocabulary size
- 128,256
- RoPE base
- 500000
- Stored precision
- float16
- Model type
- llama
Identity and Version
- Repository
- maxlabs-ai/DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16
- Publisher
- MAXLABS
- Task
- Not stated by the source
- Modality
- Other
- Library
- mlx
- Parameters
- 8B parameters
- Languages
- mlx, oq
- Revision
- c2a142d6d507edcd649a988277e9140d8c6f5c38
- First published
- 2026-09-26
- Last updated
- 2026-09-26
Files and Weights
10 files, 8.5 GB in total. The weights are 2 files totalling 8.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00002.safetensors | Weights | 5.0 GB | a428d103ea91 |
| model-00002-of-00002.safetensors | Weights | 3.5 GB | ae38c48e9fc4 |
| config.json | Configuration | 997 B | — |
| generation_config.json | Configuration | 181 B | — |
| model.safetensors.index.json | Configuration | 60.5 KB | — |
| oq_imatrix_report.json | Configuration | 11.6 KB | — |
| README.md | Documentation | 521 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 9.1 MB | — |
| tokenizer_config.json | Tokenizer | 3.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 8.5 GB
Released by MAXLABS through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 8.5 GB |
| 16-bit | 16.1 GB |
| 8-bit | 8.0 GB |
| 4-bit | 4.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16
How much GPU memory does DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16 need?
About 19.3 GB at 16-bit and 4.8 GB at 4-bit: the weights (8B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16 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 DeepSeek-R1-Distill-Llama-8B-oQ8e-fp16's context length?
131,072 tokens, from the maximum position embeddings in its published configuration.