SambaStack Supported Models and Bundles

SambaStack supports a variety of models that can be deployed to both on-prem and hosted environments. Contact your system administrator to determine which models are available on your deployment. For definitions of the Preview and Production designations, see the Glossary.

Deployment options

When deploying models in SambaStack, administrators can select from various context length and batch size combinations.

Smaller batch sizes provide higher token throughput (tokens/second).
Larger batch sizes provide better concurrency for multiple users.

SambaStack supports two deployment configurations – high-interactivity and high-throughput. See High-throughput deployment for when to use each.

Finding models on your cluster

You can run the following command to discover available models in your cluster:

kubectl -n <namespace> get models

All supported models

Search or filter to find a model, then select it to jump to its full configuration.

MiniMax

MiniMax-M2.7

MiniMax-M2.5

Mistral AI

Mistral-Large-3-675B-Instruct-2512

DeepSeek

DeepSeek-R1-0528

DeepSeek-R1-Distill-Llama-70B

DeepSeek-V3-0324

DeepSeek-V3.1

DeepSeek-V3.2

DeepSeek-V3.1-Terminus

OpenAI

gpt-oss-120b

gpt-oss-20b

Whisper-Large-v3

Google

gemma-3-27b-it

gemma-3-12b-it

gemma-4-31B-it

Alibaba Cloud

Qwen3-235B-A22B-Instruct-2507

Qwen3-32B

Qwen3-TTS-Talker

Qwen3-TTS-Vocoder

Tokyotech-llm

Llama-3.3-Swallow-70B-Instruct-v0.4

Other

E5-Mistral-7B-Instruct

Recommended model bundles

In SambaStack, models are not deployed individually; they are deployed as bundles. A bundle is a packaged deployment that groups one or more models together with their associated configurations, such as batch size and sequence length. For example, deploying the Meta‑Llama‑3.3‑70B model with a batch size of 4 and a sequence length of 16K tokens constitutes a single configuration. A bundle, however, can contain multiple such configurations, either for the same model or for different models. SambaNova’s RDU technology enables several models and configurations to be loaded simultaneously in a single deployment. This allows you to switch instantly between models and between batch‑/sequence‑size profiles as needed. In contrast to traditional GPU systems, where deployments are typically single‑model and static, SambaStack supports multi‑model, multi‑configuration bundles. This approach delivers higher efficiency, greater flexibility, and increased throughput while preserving low latency. You can run the following command to discover available bundles in your cluster:

kubectl -n <namespace> get bundles

The table below lists the recommended bundle templates for the models currently available in SambaStack. Each entry pairs a model with its recommended deployment bundle.

If the bundles listed below do not satisfy your inference requirements, you can create custom bundles that combine any mix of models and configurations so long as they fit in DDR memory.

Suggested bundles per model

For each model, this section lists the suggested bundle for typical use and any alternative bundles that trade off context length, batch size, or modality support. See Bundle configurations below for the seq length/batch size details of each bundle.

MiniMax

MiniMax-M2.7^PREVIEWSuggested: dyt-minimax-m2p7-32-64-192k-pcAlternatives: dyt-minimax-m2p7-32-160-192k, dyt-minimax-m2p7-32k-v2

MiniMax-M2.5Suggested: dyt-minimax-m2p5-32-160kAlternatives: dyt-minimax-m2p5-32k

Mistral AI

Mistral-Large-3-675B-Instruct-2512^PREVIEWSuggested: mistral-large-3-fp8-8-16-32kAlternatives: mistral-large-3-fp8-8k

DeepSeek

DeepSeek-R1-0528Suggested:

deepseek-5in1-fp8-16-32k (higher interactivity)
deepseek-4in1-fp8-128k (higher context length)

Alternatives: deepseek-r1-v3-fp8-8k, deepseek-r1-v31-fp8-8k

DeepSeek-V3-0324Suggested:

deepseek-5in1-fp8-16-32k (higher interactivity)
deepseek-4in1-fp8-128k (higher context length)

Alternatives: deepseek-r1-v3-fp8-8k, deepseek-v3-v31-fp8-8k, deepseek-v3-v3termi-fp8-8k

DeepSeek-V3.1Suggested:

deepseek-5in1-fp8-16-32k (higher interactivity)
deepseek-4in1-fp8-128k (higher context length)

Alternatives: deepseek-r1-v31-fp8-8k, deepseek-v3-v31-fp8-8k

DeepSeek-V3.1-TerminusSuggested:

deepseek-5in1-fp8-16-32k (higher interactivity)
deepseek-4in1-fp8-128k (higher context length)

Alternatives: deepseek-v3-v3termi-fp8-8k

DeepSeek-V3.2Suggested:

deepseek-5in1-fp8-16-32k (higher interactivity)
deepseek-4in1-fp8-128k (higher context length)

OpenAI

gpt-oss-120bSuggested: us-agentic-rag-1-1Alternatives: cd-dyt-gpt-oss-120b-8-32-64-128k, gpt-gemma-whisper-mistral

gpt-oss-20b^PREVIEWSuggested: dyt-gpt-oss-20b-32-64-128k

Whisper-Large-v3Suggested: qwen3-32b-whisper-e5-mistralAlternatives: 70b-3dot3-ss-full-whisper (known issue: does not load within default startup time), gpt-gemma-whisper-mistral

Google

gemma-3-27b-it^PREVIEWSuggested: gemma3-27b-32-128k

gemma-3-12b-it^PREVIEWSuggested: gemma3-v3Alternatives: gpt-gemma-whisper-mistral

gemma-4-31B-it^PREVIEWSuggested:

cd-gemma-4-31b-32-128-256k (text only; higher context length and constrained decoding support, no image/video support)
gemma-4-31b-32-128k (image/video support, higher throughput)

Alibaba Cloud

Qwen3-235B-A22B-Instruct-2507Suggested: dyt-qwen3-235b-32-128k

Qwen3-32BSuggested: qwen3-32b-whisper-e5-mistralAlternatives: qwen3-32b-llama405b-s-m

Qwen3-TTS-Talker^PREVIEWSuggested: qwen3-tts-talker

Qwen3-TTS-Vocoder^PREVIEWSuggested: qwen3-tts-vocoder

Other

E5-Mistral-7B-InstructSuggested: us-agentic-rag-1-1Alternatives: e5-mistral-70b-64k-128k, qwen3-32b-whisper-e5-mistral, gpt-gemma-whisper-mistral

Bundle configurations

The table below lists the configuration details for each bundle template referenced above.

Model name	Bundle template	Bundle description	Bundle configuration
`DeepSeek-R1-0528` / `DeepSeek-V3.1`	deepseek-r1-v31-fp8-8k	Medium context length with low batch size	View Models: `DeepSeek-R1-0528` Seq Length: 8K, BS: 1, 4 `DeepSeek-V3.1` Seq Length: 8K, BS: 1, 4
`DeepSeek-R1-0528` / `DeepSeek-V3-0324`	deepseek-r1-v3-fp8-8k	Medium context length with low batch size	View Models: `DeepSeek-R1-0528` Seq Length: 8K, BS: 1, 4 `DeepSeek-V3-0324` Seq Length: 8K, BS: 1, 4
`DeepSeek-V3-0324` / `DeepSeek-V3.1`	deepseek-v3-v31-fp8-8k	Medium context length with low batch size	View Models: `DeepSeek-V3-0324` Seq Length: 8K, BS: 1, 4 `DeepSeek-V3.1` Seq Length: 8K, BS: 1, 4
`DeepSeek-V3-0324` / `DeepSeek-V3.1-Terminus`	deepseek-v3-v3termi-fp8-8k	Medium context length with low batch size	View Models: `DeepSeek-V3-0324` Seq Length: 8K, BS: 1, 4 `DeepSeek-V3.1-Terminus` Seq Length: 8K, BS: 1, 4
`DeepSeek-R1-0528` / `DeepSeek-V3-0324` / `DeepSeek-V3.1` / `DeepSeek-V3.1-Terminus`	deepseek-4in1-fp8-128k	Large context length with single batch size Four DeepSeek models in one bundle	View Models: `DeepSeek-R1-0528` Seq Length: 128K, BS: 1 `DeepSeek-V3-0324` Seq Length: 128K, BS: 1 `DeepSeek-V3.1` Seq Length: 128K, BS: 1 `DeepSeek-V3.1-Terminus` Seq Length: 128K, BS: 1
`DeepSeek-R1-0528` / `DeepSeek-V3-0324` / `DeepSeek-V3.1` / `DeepSeek-V3.1-Terminus` / `DeepSeek-V3.2`	deepseek-5in1-fp8-16-32k	Medium context length with single batch size Five DeepSeek models in one bundle	View Models (each): Seq Length: 16K, BS: 1 Seq Length: 32K, BS: 1
`E5-Mistral-7B-Instruct` / `Meta-Llama-3.1-8B-Instruct` / `Llama-4-Maverick-17B-128E-Instruct` / `Meta-Llama-3.3-70B-Instruct` / `gpt-oss-120b`	us-agentic-rag-1-1	Small to medium context length with varied batch size Speculative decoding supported for `Meta-Llama-3.3-70B`	View `gpt-oss-120b` Seq Length: 32K, BS: 4 Seq Length: 64K, BS: 2 Seq Length: 128K, BS: 2 `Llama-4-Maverick-17B-128E-Instruct` Seq Length: 8K, BS: 1 Seq Length: 16K, BS: 1 `Meta-Llama-3.3-70B` (Target)/ `Meta-Llama-3.2-1B` (Draft) Seq Length: 4K, BS: 1, 4, 8, 16, 32 Seq Length: 8K, BS: 1, 4, 8 Seq Length: 16K, BS: 1, 4 Seq Length: 32K, BS: 1, 4 Seq Length: 64K, BS: 1 Seq Length: 128K, BS: 1 `Meta-Llama-3.1-8B-Instruct` Seq Length: 4K, BS: 1, 4, 16, 32 Seq Length: 8K, BS: 1, 4, 16, 32 Seq Length: 16K, BS: 1, 4, 8 `E5-Mistral-7B-Instruct` Seq Length: 4K, BS: 1, 4, 8, 16, 32
`E5-Mistral-7B-Instruct` / `Meta-Llama-3.3-70B`	e5-mistral-70b-64k-128k	Large context length with low batch size Speculative decoding supported for `Meta-Llama-3.3-70B`	View Models: `E5-Mistral-7B-Instruct` Seq Length: 4K, BS: 1, 4, 8, 16, 32 `Meta-Llama-3.3-70B` (Target)/ `Meta-Llama-3.2-1B` (Draft) Seq Length: 64K, BS: 1 Seq Length: 128K, BS: 1
`gemma-3-27b-it`	gemma3-27b-32-128k	Homogeneous bundle containing `gemma-3-27b-it` configurations.	View `gemma-3-27b-it` Seq Length: 32K, BS: 2, 4, 6, 8 Seq Length: 128K, BS: 2, 4, 6, 8
`gemma-3-12b-it`	gemma3-v3	Homogeneous bundle containing `gemma-3-12b-it` configurations. Large context length with medium batch size	View `gemma-3-12b-it` Seq Length: 128K, BS: 2, 4, 6, 8
`gemma-4-31B-it`	gemma-4-31b-32-128k	Homogeneous bundle containing `gemma-4-31B-it` configurations.	View `gemma-4-31B-it` Seq Length: 32K, BS: 2, 4, 6, 8 Seq Length: 128K, BS: 2, 4, 6, 8
`gemma-4-31B-it`	`cd-gemma-4-31b-32-128-256k`^PREVIEW	Homogeneous bundle with constrained decoding for `gemma-4-31B-it`. Adds 32K–256K context support (preview). Image and video inputs have known accuracy issues across all sequence lengths in this bundle.	View `gemma-4-31B-it` Seq Length: 32K, BS: 2 Seq Length: 128K, BS: 2 Seq Length: 256K, BS: 2
`gpt-oss-120b`	`cd-dyt-gpt-oss-120b-32-64-128k` † `cd-dyt-gpt-oss-120b-8-32-64-128k` †	Homogeneous bundles with constrained decoding for `gpt-oss-120b`. `cd-dyt-gpt-oss-120b-8-32-64-128k` adds 8K context support. Refreshed PEFs include structured output (logit-masking) support.	View `cd-dyt-gpt-oss-120b-32-64-128k` Seq Length: 32K, BS: 2, 4, 6, 8 Seq Length: 64K, BS: 2, 4 Seq Length: 128K, BS: 2 `cd-dyt-gpt-oss-120b-8-32-64-128k` Seq Length: 8K, BS: 2, 4, 6, 8 Seq Length: 32K, BS: 2, 4, 6, 8 Seq Length: 64K, BS: 2, 4 Seq Length: 128K, BS: 2
`gpt-oss-20b`	`dyt-gpt-oss-20b-32-64-128k` †	Homogeneous bundle with constrained decoding for `gpt-oss-20b`.	View `dyt-gpt-oss-20b-32-64-128k` Seq Length: 8K, BS: 2, 4, 6, 8 Seq Length: 32K, BS: 2, 4, 6, 8 Seq Length: 64K, BS: 2, 4 Seq Length: 128K, BS: 2
`E5-Mistral-7B-Instruct` / `Whisper-Large-v3` / `gemma-3-12b-it` / `gpt-oss-120b`	gpt-gemma-whisper-mistral	Small to medium context length combining embeddings, transcription, image understanding, and a tool-calling agent	View Models: `E5-Mistral-7B-Instruct` Seq Length: 4K, BS: 1 `Whisper-Large-v3` BS: 1 `gemma-3-12b-it` Seq Length: 128K, BS: 2, 4, 6, 8 `gpt-oss-120b` Seq Length: 8K, BS: 2, 4, 6, 8
`Llama-4-Maverick-17B-128E-Instruct`	llama-4-medium-8-16-32-64-128k	Homogeneous bundles containing `Llama-4-Maverick-17B-128E-Instruct` configurations. Small to large context length with low batch	View `Llama-4-Maverick-17B-128E-Instruct` Seq Length: 8K, BS: 1 Seq Length: 16K, BS: 1 Seq Length: 32K, BS: 1 Seq Length: 64K, BS: 1 Seq Length: 128K, BS: 1
`Llama-4-Maverick-17B-128E-Instruct`	llama-4-medium-ss-16k-bs24	Homogeneous bundle containing `Llama-4-Maverick-17B-128E-Instruct` configurations; medium context length with higher batch size.	View `Llama-4-Maverick-17B-128E-Instruct` Seq Length: 16K, BS: 2, 4
`Meta-Llama-3.3-70B-Instruct`	70b-3dot3-ss-4-8-16-32-64-128k	Medium to large context length with low batch size	View Target Models: `Meta-Llama-3.3-70B-Instruct` Seq Length: 4K, BS: 2, 4, 8, 16, 32 Seq Length: 8K, BS: 2, 4, 8, 16, 32 Seq Length: 16K, BS: 1, 2, 4 Seq Length: 32K, BS: 1, 2, 4 Seq Length: 64K, BS: 1, 2, 4 Seq Length: 128K, BS: 1 Draft Models: `Meta-Llama-3.2-1B-Instruct` Seq Length: 4K, BS: 2, 4, 8, 16, 32 Seq Length: 8K, BS: 2, 4, 8, 16, 32 Seq Length: 16K, BS: 1, 2, 4 Seq Length: 32K, BS: 1, 2, 4 Seq Length: 64K, BS: 1, 2, 4; private: true Seq Length: 128K, BS: 1; private: true
`Meta-Llama-3.3-70B-Instruct` / `Whisper-Large-v3`	70b-3dot3-ss-full-whisper	Full context-length range with low to medium batch size, plus Whisper transcription Speculative decoding supported for `Meta-Llama-3.3-70B-Instruct`	View Target Models: `Meta-Llama-3.3-70B-Instruct` Seq Length: 4K, BS: 2, 4, 8, 16, 32 Seq Length: 8K, BS: 2, 4, 8, 16, 32 Seq Length: 16K, BS: 1, 2, 4 Seq Length: 32K, BS: 1, 2, 4 Seq Length: 64K, BS: 1, 2, 4 Seq Length: 128K, BS: 1 `Whisper-Large-v3` BS: 1, 16, 32 Draft Models: `Meta-Llama-3.2-1B-Instruct` Seq Length: 4K, BS: 2, 4, 8, 16, 32 Seq Length: 8K, BS: 2, 4, 8, 16, 32 Seq Length: 16K, BS: 1, 2, 4 Seq Length: 32K, BS: 1, 2, 4 Seq Length: 64K, BS: 1, 2, 4 Seq Length: 128K, BS: 1
`MiniMax-M2.5`	dyt-minimax-m2p5-32k dyt-minimax-m2p5-32-160k	Homogeneous bundles containing `MiniMax-M2.5` configurations. dyt-minimax-m2p5-32k is better for medium sequence lengths and high batching. dyt-minimax-m2p5-32-160k is better for higher sequence lengths and low batching	View dyt-minimax-m2p5-32k Seq Length: 4K-32K, BS: 2, 4, 6, 8 dyt-minimax-m2p5-32-160k Seq Length: 32K, BS: 2 Seq Length: 160K, BS: 2
`MiniMax-M2.7`^PREVIEW	dyt-minimax-m2p7-32k-v2	Homogeneous bundle containing `MiniMax-M2.7` configurations; medium context length with high batching.	View `MiniMax-M2.7` Seq Length: 8K-32K, BS: 2, 4, 6, 8
`MiniMax-M2.7`^PREVIEW	dyt-minimax-m2p7-32-160-192k	Homogeneous bundle containing `MiniMax-M2.7` configurations; better for higher sequence lengths and low batching.	View `MiniMax-M2.7` Seq Length: 8K-32K, BS: 2, 4, 6, 8 Seq Length: 160K-192K, BS: 2
`MiniMax-M2.7`^PREVIEW	dyt-minimax-m2p7-32-64-192k-pc	Homogeneous bundle with prompt caching for `MiniMax-M2.7`.	View `MiniMax-M2.7` Seq Length: 32K-192K, BS: 2, 4, 6, 8
`Mistral-Large-3-675B-Instruct-2512`^PREVIEW	mistral-large-3-fp8-8k	Homogeneous bundle containing `Mistral-Large-3-675B-Instruct-2512` configurations. Preview model – text-only.	View `Mistral-Large-3-675B-Instruct-2512` Seq Length: 8K, BS: 1
`Mistral-Large-3-675B-Instruct-2512`^PREVIEW	mistral-large-3-fp8-8-16-32k	Homogeneous bundle containing `Mistral-Large-3-675B-Instruct-2512` configurations. Wider context range than `mistral-large-3-fp8-8k`. Preview model – text-only.	View `Mistral-Large-3-675B-Instruct-2512` Seq Length: 8K, BS: 1, 4 Seq Length: 16K, BS: 1, 2 Seq Length: 32K, BS: 1
`Qwen3-235B-A22B-Instruct-2507`	dyt-qwen3-235b-32-128k	Homogeneous bundle containing `Qwen3-235B-A22B-Instruct-2507` configurations.	View `Qwen3-235B-A22B-Instruct-2507` Seq Length: 32K, BS: 2, 4, 6, 8 Seq Length: 128K, BS: 2
`Whisper-Large-v3` / `Qwen3-32B` / `E5-Mistral-7B-Instruct`	qwen3-32b-whisper-e5-mistral	Small to medium context length with varied batch size	View `E5-Mistral-7B-Instruct` Seq Length: 4K, BS: 1, 4, 8, 16, 32 `Qwen3-32B` Seq Length: 8K, BS: 1, 4 Seq Length: 16K, BS: 1 Seq Length: 32K, BS: 1, 2 `Whisper-Large-v3` BS: 1, 16, 32
`Qwen3-32B` / `Meta-Llama-3.1-405B-Instruct`	qwen3-32b-llama405b-s-m	Small to medium context length Speculative decoding supported for `Meta-Llama-3.1-405B-Instruct`	View Target Models: `Meta-Llama-3.1-405B-Instruct` Seq Length: 4K, BS: 1, 2, 4 Seq Length: 8K, BS: 1 Seq Length: 16K, BS: 1 Draft Models: `Meta-Llama-3.1-8B-Instruct` Seq Length: 16K, BS: 1 `Meta-Llama-3.2-3B-Instruct` Seq Length: 4K, BS: 1, 2, 4 Seq Length: 8K, BS: 1 Routable Models: `Qwen3-32B` Seq Length: 8K, BS: 1, 4 Seq Length: 16K, BS: 1 Seq Length: 32K, BS: 1
`Qwen3-TTS-Talker`^PREVIEW	qwen3-tts-talker	Homogeneous bundle containing `Qwen3-TTS-Talker` configurations.	View `Qwen3-TTS-Talker` Seq Length: 4K, BS: 2
`Qwen3-TTS-Vocoder`^PREVIEW	qwen3-tts-vocoder	Homogeneous bundle containing `Qwen3-TTS-Vocoder` configurations.	View `Qwen3-TTS-Vocoder` Seq Length: 4K, BS: 1

† These bundles support sequence lengths from 8K–128K. If you require shorter context lengths (4K–16K) for gpt-oss-120b, contact your SambaNova representative.

​Deployment options

​Finding models on your cluster

​All supported models

​Meta

​Meta-Llama-3.3-70B-Instruct

​Meta-Llama-3.1-8B-Instruct

​Meta-Llama-3.1-70B-Instruct

​Meta-Llama-3.1-405B-Instruct

​Llama-4-Maverick-17B-128E-Instruct

​MiniMax

​MiniMax-M2.7

​MiniMax-M2.5

​Mistral AI

​Mistral-Large-3-675B-Instruct-2512

​DeepSeek

​DeepSeek-R1-0528

​DeepSeek-R1-Distill-Llama-70B

​DeepSeek-V3-0324

​DeepSeek-V3.1

​DeepSeek-V3.2

​DeepSeek-V3.1-Terminus

​OpenAI

​gpt-oss-120b

​gpt-oss-20b

​Whisper-Large-v3

​Google

​gemma-3-27b-it

​gemma-3-12b-it

​gemma-4-31B-it

​Alibaba Cloud

​Qwen3-235B-A22B-Instruct-2507

​Qwen3-32B

​Qwen3-TTS-Talker

​Qwen3-TTS-Vocoder

​Tokyotech-llm

​Llama-3.3-Swallow-70B-Instruct-v0.4

​Other

​E5-Mistral-7B-Instruct

​Recommended model bundles

​Suggested bundles per model

​Meta

​MiniMax

​Mistral AI

​DeepSeek

​OpenAI

​Google

​Alibaba Cloud

​Other

​Bundle configurations

Deployment options

Finding models on your cluster

All supported models

Meta

Meta-Llama-3.3-70B-Instruct

Meta-Llama-3.1-8B-Instruct

Meta-Llama-3.1-70B-Instruct

Meta-Llama-3.1-405B-Instruct

Llama-4-Maverick-17B-128E-Instruct

MiniMax

MiniMax-M2.7

MiniMax-M2.5

Mistral AI

Mistral-Large-3-675B-Instruct-2512

DeepSeek

DeepSeek-R1-0528

DeepSeek-R1-Distill-Llama-70B

DeepSeek-V3-0324

DeepSeek-V3.1

DeepSeek-V3.2

DeepSeek-V3.1-Terminus

OpenAI

gpt-oss-120b

gpt-oss-20b

Whisper-Large-v3

Google

gemma-3-27b-it

gemma-3-12b-it

gemma-4-31B-it

Alibaba Cloud

Qwen3-235B-A22B-Instruct-2507

Qwen3-32B

Qwen3-TTS-Talker

Qwen3-TTS-Vocoder

Tokyotech-llm

Llama-3.3-Swallow-70B-Instruct-v0.4

Other

E5-Mistral-7B-Instruct

Recommended model bundles

Suggested bundles per model

Meta

MiniMax

Mistral AI

DeepSeek

OpenAI

Google

Alibaba Cloud

Other

Bundle configurations