Qwen

Qwen2.5-Omni-7B

← All models

10.7B parameters · Base · Qwen2.5 family

apache-2.0 hash verified source matched revision pinned

Which version should I download?

Default pick: safetensors · BF16 — Official Qwen BF16 safetensors — full Qwen2.5-Omni-7B package (thinker+talker, audio+vision encoders, spk_dict): text/audio/image/video input + speech output. Modality-lane full-capability entry. Apache-2.0.

Set your rig to confirm it fits and to see if a higher-quality quant runs fully on your hardware.

Set your rig

Quantizations

Why these quants? Which quant should I pick?

safetensors · BF16

20.83 GB

Set your rig
Est. speed
—
Swarm
2S / 0L webseed OK

Official Qwen BF16 safetensors — full Qwen2.5-Omni-7B package (thinker+talker, audio+vision encoders, spk_dict): text/audio/image/video input + speech output. Modality-lane full-capability entry. Apache-2.0.

Magnet .torrent

Run it

Runtime completeness (BF16 torrent): llama.cpp – Ollama – vision sidecar –

  • – llama.cpp — no GGUF artifact for this torrent
  • – Ollama — not an Ollama-native artifact
  • – vision sidecar — not a vision model

Context / KV 8,192 tokens · FP16 set above the quant table

Generic commands (no rig set). GPU-offload values assume the model fits on your GPU — set your rig for values tuned to your hardware.

Start the server 
llama-server -m qwen-qwen2-5-omni-7b-BF16.gguf -c 8192 -ngl 999

Use llama-cli in place of llama-server for a one-shot prompt.

Save as Modelfile next to the GGUF (Modelfile) 
FROM ./qwen-qwen2-5-omni-7b-BF16.gguf
PARAMETER num_ctx 8192
PARAMETER num_gpu 999
Create 
ollama create qwen-qwen2-5-omni-7b -f Modelfile
Run 
ollama run qwen-qwen2-5-omni-7b
Serve an OpenAI-compatible endpoint 
vllm serve Qwen/Qwen2.5-Omni-7B --max-model-len 8192

Serves on http://localhost:8000/v1 by default.

Load qwen-qwen2-5-omni-7b-BF16.gguf, set the context length to 8192 tokens. Set GPU offload to Max (all layers).

Not an MLX-format quant.

MLX runs MLX-format weights only (Apple Silicon). This quant is not an MLX build.

Filename shown is a placeholder. The exact GGUF name appears once the download is available.

Technical details

No template or sampling metadata recorded.

Evidence & provenance

Source

Provenance
https://huggingface.co/Qwen/Qwen2.5-Omni-7B
Revision pin
ae9e1690543ffd5c0221dc27f79834d0294cba00
Manifest
Present

License

Name
apache-2.0
Commercial use
yes
Access
Open
Notes
Authoritative upstream Qwen/Qwen2.5-Omni-7B: HF card tags license:other but license_name=apache-2.0 with license_link to the repo Apache-2.0 LICENSE (11,343 B, Qwen-flavored). Entire Qwen2.5/Qwen3 open release is Apache-2.0. Corrected other->apache-2.0 (precedent Qwen3-Omni #98).

File hashes (SHA-256)

  • qwen2-5-omni-7b/.gitattributes 34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
  • qwen2-5-omni-7b/LICENSE 8d5eb5f806d01e8f5ea2c5a52f7d68ebc54b196b1cfbe1cd5dfa4b94e482a9c6
  • qwen2-5-omni-7b/README.md 56f828c01cf5a3073a3968883c4dcbfef715af67b9295b66eb4d4941eef1680e
  • qwen2-5-omni-7b/added_tokens.json e81a2cc3bd867a1217019eed202d1d8a07e1063ece716f22060dda14f6cc07d8
  • qwen2-5-omni-7b/chat_template.json 1933f7ca08e6503460e981d9037ddc0b851196abfa3aceea52d6ee0c0fdfd9f0
  • qwen2-5-omni-7b/config.json f85f5a078951471e32d6ce5dd169acf619e3480c83daf195e5016ef3eb89b1a9
  • qwen2-5-omni-7b/generation_config.json b9acf52072249e0e1850541d51ca4c85a30b9d7e23c2f2093ec0fb4139059ac7
  • qwen2-5-omni-7b/merges.txt 8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
  • qwen2-5-omni-7b/model-00001-of-00005.safetensors 5edb02fd7c98803239468375cc9dc1bff492865c2aa086b78f348597021d6cbc
  • qwen2-5-omni-7b/model-00002-of-00005.safetensors 7c99b55c6e5bc63fd4b19d4dc23cdc3ddac4b0101bb3c0958cc2b5d05c2bbafe
  • qwen2-5-omni-7b/model-00003-of-00005.safetensors ad00c3ac296300db905934ed213c4077ff49b85d30c0099270c814e2c77ec812
  • qwen2-5-omni-7b/model-00004-of-00005.safetensors 152bc7d81441eaba22547d8d96c03d32dd592ce0e0e1d0e449347a4b23a532d3
  • qwen2-5-omni-7b/model-00005-of-00005.safetensors b8b18276481ba8cdf4fe2c98ac4c7a2da6e0d1c8a51850d162a391760cb2b81e
  • qwen2-5-omni-7b/model.safetensors.index.json 5428b3927da9f3bd525967db81936642e4e068afc3f8f2dfaf2a9066c9bef8e2
  • qwen2-5-omni-7b/preprocessor_config.json b47055ce61463ce143e9aab741d55c0aa520801a0a5d63be73c5b17cecb6bc69
  • qwen2-5-omni-7b/special_tokens_map.json dc241604d085780a33f760f69c47e6622451104c20eee3cd3a12b6e884b43f44
  • qwen2-5-omni-7b/spk_dict.pt 6a05609b28f5d42b7b748f0f07592545c8f1f6885b9ae8fff64baf56e86b2a18
  • qwen2-5-omni-7b/tokenizer.json 8441917e39ae0244e06d704b95b3124795cec478e297f9afac39ba670d7e9d99
  • qwen2-5-omni-7b/tokenizer_config.json 569aa7a9171e36dfff80f0a7550ab0c9c09e46ac840fea5030641417394fb0d2
  • qwen2-5-omni-7b/vocab.json ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

Performance reports

Real-world throughput reported by the community (and scraped sources).

View performance leaderboard

Reviews & presets

Reviews (0)

Log in to write a structured review of this model.

No reviews yet.

Sampler presets

Log in to share a sampler preset or vote on presets.

No presets yet.

Community runtime reports

Unofficial, community-submitted "it loads for me" reports. These are not the official verified-working badge — an admin reviews reports before anything is marked officially verified.

Log in to report whether a quant loads in your runtime.

No community reports yet.

selected to compare · pick at least 2

Compare ()