Catalogue

every model we serve, and what it really costs

One OpenAI-compatible endpoint, open weights only, priced per million tokens with no minimum and no subscription. Each model reaches several classes of GPU through different quantizations, so a 6 GB card and a 24 GB card both have work to do — and hosts keep 80% of what their hardware earns.

what your GPU can serve

Your card	Models	For example
6 GB	3	Gemma 4 E4B Instruct, Qwen2.5 1.5B Instruct, Qwen2.5 0.5B Instruct
8 GB	3	Gemma 4 E4B Instruct, Qwen2.5 1.5B Instruct, Qwen2.5 0.5B Instruct
10 GB	5	Qwen3.8 27B Instruct, Gemma 4 12B Instruct, Gemma 4 E4B Instruct
12 GB	5	Qwen3.8 27B Instruct, Gemma 4 12B Instruct, Gemma 4 E4B Instruct
16 GB	6	Qwen3.8 27B Instruct, gpt-oss 20B, Gemma 4 12B Instruct
24 GB	7	Qwen3.8 27B Instruct, Gemma 4 26B-A4B Instruct, gpt-oss 20B

Minimum VRAM per build. Install mahout and run mahout models — it tells you exactly what your own card can serve.

Qwen3.8 27B Instruct

qwen3.8-27b

2026 flagship open model for a single card: strong reasoning and code, 262K context, and no EU-sovereign listing anywhere else.

chatcodereasoninglong-contextmultilingualtool-use

size: 27B dense
max context: 256K tokens
licence: Apache-2.0
price: €0.25 in · €0.75 out per million tokens
smallest card: from 9 GB VRAM

5 build(s) — one per VRAM class

quantization	download	needs	context	notes
`UD-Q5_K_M`	18.4 GB	23 GB VRAM	16K	reference quality
`UD-Q4_K_M`	15.3 GB	20 GB VRAM	16K	reference quality
`UD-Q3_K_XL`	12.2 GB	16 GB VRAM	8K	balanced
`UD-Q2_K_XL`	9.2 GB	12 GB VRAM	8K	compact — fits smaller cards
`UD-IQ2_XXS`	6.8 GB	9 GB VRAM	8K	compact — fits smaller cards

Every build is pinned to an exact upstream revision and verified against its SHA-256 before it runs — on your machine if you host, and on the machine serving you if you build.

Gemma 4 26B-A4B Instruct

gemma-4-26b-a4b

Mixture-of-experts: 26B of knowledge at the speed of a 4B model. Quantization-aware weights published by Google, so the 4-bit build loses far less than a post-hoc quantization.

chatreasoningmultilinguallong-context

size: 26B MoE, 4B active
max context: 128K tokens
licence: Gemma Terms of Use
price: €0.15 in · €0.45 out per million tokens
smallest card: from 17 GB VRAM

1 build(s) — one per VRAM class

quantization	download	needs	context	notes
`Q4_0 (QAT)`	13.4 GB	17 GB VRAM	8K	reference quality

Every build is pinned to an exact upstream revision and verified against its SHA-256 before it runs — on your machine if you host, and on the machine serving you if you build.

gpt-oss 20B

gpt-oss-20b

Open-weight 20B tuned for tool use and structured output. Natively MXFP4, so 4-bit costs it almost nothing.

chatcodetool-usereasoning

size: 20B MoE
max context: 128K tokens
licence: Apache-2.0
price: €0.12 in · €0.4 out per million tokens
smallest card: from 14 GB VRAM

1 build(s) — one per VRAM class

quantization	download	needs	context	notes
`Q4_K_M`	10.8 GB	14 GB VRAM	8K	reference quality

Every build is pinned to an exact upstream revision and verified against its SHA-256 before it runs — on your machine if you host, and on the machine serving you if you build.

Gemma 4 12B Instruct

gemma-4-12b

The 8 GB workhorse: a capable general assistant on cards most gamers already own, with Google's quantization-aware 4-bit weights.

chatreasoningmultilingual

size: 12B dense
max context: 128K tokens
licence: Gemma Terms of Use
price: €0.08 in · €0.25 out per million tokens
smallest card: from 10 GB VRAM

1 build(s) — one per VRAM class

quantization	download	needs	context	notes
`Q4_0 (QAT)`	6.5 GB	10 GB VRAM	8K	reference quality

Every build is pinned to an exact upstream revision and verified against its SHA-256 before it runs — on your machine if you host, and on the machine serving you if you build.

Gemma 4 E4B Instruct

gemma-4-e4b

Built for small cards and laptops: 6 GB of VRAM is enough to earn.

chatmultilingual

size: 8B MatFormer, 4B effective
max context: 128K tokens
licence: Gemma Terms of Use
price: €0.05 in · €0.15 out per million tokens
smallest card: from 6 GB VRAM

1 build(s) — one per VRAM class

quantization	download	needs	context	notes
`Q4_0 (QAT)`	4.8 GB	6 GB VRAM	8K	reference quality

Every build is pinned to an exact upstream revision and verified against its SHA-256 before it runs — on your machine if you host, and on the machine serving you if you build.

Qwen2.5 1.5B Instruct

qwen2.5-1.5b-instruct

Tiny, fast, runs anywhere — the enrollment smoke test and the model behind starter work for a freshly linked machine.

chat

size: 1.5B dense
max context: 32K tokens
licence: Apache-2.0
price: €0.05 in · €0.15 out per million tokens
smallest card: from 3 GB VRAM

1 build(s) — one per VRAM class

quantization	download	needs	context	notes
`Q4_K_M`	1 GB	3 GB VRAM	8K	reference quality

Every build is pinned to an exact upstream revision and verified against its SHA-256 before it runs — on your machine if you host, and on the machine serving you if you build.

Qwen2.5 0.5B Instruct

qwen2.5-0.5b-instruct

Smallest catalog entry: CPU-only fallback and multi-model swap tests.

chat

size: 0.5B dense
max context: 32K tokens
licence: Apache-2.0
price: €0.02 in · €0.06 out per million tokens
smallest card: from 2 GB VRAM

1 build(s) — one per VRAM class

quantization	download	needs	context	notes
`Q4_K_M`	0.5 GB	2 GB VRAM	8K	reference quality

Every build is pinned to an exact upstream revision and verified against its SHA-256 before it runs — on your machine if you host, and on the machine serving you if you build.

use them, or serve them

Point your SDK's base URL at https://app.elephantpool.ai/api/gateway/v1 and pass the model id — or connect a GPU and get paid for every token it produces.

Serve with your GPU Call the API