Open-weight model
gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929
by doyoon Kim cosmos1030/gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929
gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929 is an open-weight model from doyoon Kim. It has 1.7B parameters and a 40,960-token context. At 16-bit it needs about 4.1 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 gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929 (1.7B 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 | 3.4 GB | 4.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.7 GB | 2.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.9 GB | 1.0 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
- Qwen3ForCausalLM
- Context length (tokens)
- 40,960
- Layers
- 28
- Hidden size
- 2,048
- Feed-forward size
- 6,144
- Attention heads
- 16
- 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
- cosmos1030/gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929
- Publisher
- doyoon Kim
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 1.7B parameters
- Languages
- Not stated by the source
- Revision
- 322afc01cc162fb1c96de1cf2f9b01c6288c9b41
- First published
- 2026-10-06
- Last updated
- 2026-10-06
Files and Weights
23 files, 3.8 GB in total. The weights are 1 file totalling 3.4 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.4 GB | 08fd03127a2e |
| added_tokens.json | Configuration | 707 B | — |
| config.json | Configuration | 1.4 KB | — |
| generation_config.json | Configuration | 214 B | — |
| lighteval_bench/gpqa/results/home1/doyoonkim/projects/elsa/models/gmp_1.7b_s0pct_lr0.0001_onpol_lmda0.33_20261006_073724_p1630679/results_2026-10-06T09-10-58.150378.json | Configuration | 4.2 KB | — |
| lighteval_bench/gsm8k/results/home1/doyoonkim/projects/elsa/models/gmp_1.7b_s0pct_lr0.0001_onpol_lmda0.33_20261006_073724_p1630679/results_2026-10-06T12-29-21.578750.json | Configuration | 4.7 KB | — |
| lighteval_bench/ifeval/results/home1/doyoonkim/projects/elsa/models/gmp_1.7b_s0pct_lr0.0001_onpol_lmda0.33_20261006_073724_p1630679/results_2026-10-06T09-54-39.127262.json | Configuration | 5.3 KB | — |
| lighteval_bench/math500/results/home1/doyoonkim/projects/elsa/models/gmp_1.7b_s0pct_lr0.0001_onpol_lmda0.33_20261006_073724_p1630679/results_2026-10-06T08-28-55.675746.json | Configuration | 4.1 KB | — |
| special_tokens_map.json | Configuration | 613 B | — |
| 2f9bf915d9db2d80/lighteval|gsm8k|0/74d03fcaaa6b60e2/GENERATIVE.parquet | Other | 45.2 MB | 25cd99e8a1df |
| 4b05021d5b2d9916/lighteval|gpqa:diamond|0/2dc37638b9c80e63/GENERATIVE.parquet | Other | 30.3 MB | f5eafc6f9054 |
| 4b05021d5b2d9916/lighteval|ifeval|0/8889067d36dd85a9/GENERATIVE.parquet | Other | 36.1 MB | 832aab16d725 |
| 4b05021d5b2d9916/lighteval|math_500|0/96d15db777768a3b/GENERATIVE.parquet | Other | 40.0 MB | d4d7ba759cbf |
| chat_template.jinja | Other | 4.2 KB | — |
| lighteval_bench/gpqa/details/home1/doyoonkim/projects/elsa/models/gmp_1.7b_s0pct_lr0.0001_onpol_lmda0.33_20261006_073724_p1630679/2026-10-06T09-10-58.150378/details_lighteval|gpqa:diamond|0_2026-10-06T09-10-58.150378.parquet | Other | 37.1 MB | 1e7c8e3628dc |
| lighteval_bench/gsm8k/details/home1/doyoonkim/projects/elsa/models/gmp_1.7b_s0pct_lr0.0001_onpol_lmda0.33_20261006_073724_p1630679/2026-10-06T12-29-21.578750/details_lighteval|gsm8k|0_2026-10-06T12-29-21.578750.parquet | Other | 50.1 MB | 89538b95305d |
| lighteval_bench/ifeval/details/home1/doyoonkim/projects/elsa/models/gmp_1.7b_s0pct_lr0.0001_onpol_lmda0.33_20261006_073724_p1630679/2026-10-06T09-54-39.127262/details_lighteval|ifeval|0_2026-10-06T09-54-39.127262.parquet | Other | 44.2 MB | c880d5d2eb71 |
| lighteval_bench/math500/details/home1/doyoonkim/projects/elsa/models/gmp_1.7b_s0pct_lr0.0001_onpol_lmda0.33_20261006_073724_p1630679/2026-10-06T08-28-55.675746/details_lighteval|math_500|0_2026-10-06T08-28-55.675746.parquet | Other | 46.2 MB | 88128dc37ed5 |
| .gitattributes | Repository | 1.6 KB | — |
| merges.txt | Tokenizer | 1.7 MB | — |
| tokenizer.json | Tokenizer | 11.4 MB | aeb13307a71a |
| tokenizer_config.json | Tokenizer | 5.4 KB | — |
| vocab.json | Tokenizer | 2.8 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 3.4 GB
Released by doyoon Kim through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.4 GB |
| 16-bit | 3.4 GB |
| 8-bit | 1.7 GB |
| 4-bit | 0.9 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929
How much GPU memory does gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929 need?
About 4.1 GB at 16-bit and 1 GB at 4-bit: the weights (1.7B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929 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 gmp-kd3e-1-1.7b-s0pct-lr1e-4_20261006_122929's context length?
40,960 tokens, from the maximum position embeddings in its published configuration.