POCKET: a 35-billion-parameter model that runs on your iPhone โ and on your PC with no GPU
โข 12
AI & ML interests
Contact: arxivgpt@gmail.com
Recent Activity
View all activity
Papers
View all Papers Articles
Benchmark?
3
#1 opened 7 days ago
by 
oro872gioioso
SeaWolf-AIย
updated a
model about 11 hours ago
SeaWolf-AIย
updated 5
models about 18 hours ago
FINAL-Bench/POCKET-26B-GGUF
Text Generation โข 25B โข Updated โข 4.64k โข 36
FINAL-Bench/POCKET-KR-MLX
Text Generation โข 15B โข Updated โข 626 โข 26
FINAL-Bench/POCKET-KR-GGUF
Text Generation โข 23B โข Updated โข 1.66k โข 26
FINAL-Bench/POCKET-EN-GGUF
Text Generation โข 23B โข Updated โข 2.68k โข 33
FINAL-Bench/POCKET-35B-GGUF
Text Generation โข 35B โข Updated โข 12.2k โข 59
SeaWolf-AIย
updated a
model 2 days ago
SeaWolf-AIย
posted an update 4 days ago
Post
6324
๐ผ๏ธ POCKET-Image โ the POCKET series goes visual: character-perfect text in any language, on-device
A new model in VIDRAFT's POCKET family. POCKET put 35B-class models on phones and no-GPU PCs. POCKET-Image carries the same "big capability, small hardware" idea into image generation โ and fixes the one thing nearly every image model gets wrong: text.
Type "์๋ ํ์ธ์" into a typical model and you get "์ใ ๊ธฐ." Hangul alone composes 11,172 syllable blocks; Arabic connects its letters; Thai stacks marks. Diffusion models draw scripts as shapes, so they smear. POCKET-Image renders every glyph exactly โ ํ๊ตญ์ด ยท ไธญๆ ยท ๆฅๆฌ่ช ยท ุงูุนุฑุจูุฉ (RTL) ยท เนเธเธข ยท Latin and more โ onto any scene you describe.
What it is:
โข 100% accurate text, any language โ where global models produce gibberish
โข Any background from a prompt โ text is optional (empty โ a pure image)
โข No GPU, no NPU โ runs on plain CPU + RAM via the POCKET-Core engine
โข Measured footprint: 8.6 GB (RTX 3050/4060) ยท 4.5 GB (offloaded, 6 GB cards) ยท 13.4 GB (MacBook, 16 GB+)
โข Windows ยท macOS ยท Linux ยท fully local, no cloud
Built on the open, commercial-friendly Z-Image (Apache-2.0) foundation.
Honest note: the text is the guaranteed-correct part โ the surrounding scene is ordinary generation, so a busy foreground can crowd the letters. We say so; clean backgrounds stay razor-sharp.
๐จ Studio โ generate right here, any language:
FINAL-Bench/POCKET-Image-Studio
๐งฉ Model card:
FINAL-Bench/POCKET-Image-Zimage
๐ The POCKET collection:
https://huggingface.co/collections/FINAL-Bench/pocket-models
A new model in VIDRAFT's POCKET family. POCKET put 35B-class models on phones and no-GPU PCs. POCKET-Image carries the same "big capability, small hardware" idea into image generation โ and fixes the one thing nearly every image model gets wrong: text.
Type "์๋ ํ์ธ์" into a typical model and you get "์ใ ๊ธฐ." Hangul alone composes 11,172 syllable blocks; Arabic connects its letters; Thai stacks marks. Diffusion models draw scripts as shapes, so they smear. POCKET-Image renders every glyph exactly โ ํ๊ตญ์ด ยท ไธญๆ ยท ๆฅๆฌ่ช ยท ุงูุนุฑุจูุฉ (RTL) ยท เนเธเธข ยท Latin and more โ onto any scene you describe.
What it is:
โข 100% accurate text, any language โ where global models produce gibberish
โข Any background from a prompt โ text is optional (empty โ a pure image)
โข No GPU, no NPU โ runs on plain CPU + RAM via the POCKET-Core engine
โข Measured footprint: 8.6 GB (RTX 3050/4060) ยท 4.5 GB (offloaded, 6 GB cards) ยท 13.4 GB (MacBook, 16 GB+)
โข Windows ยท macOS ยท Linux ยท fully local, no cloud
Built on the open, commercial-friendly Z-Image (Apache-2.0) foundation.
Honest note: the text is the guaranteed-correct part โ the surrounding scene is ordinary generation, so a busy foreground can crowd the letters. We say so; clean backgrounds stay razor-sharp.
๐จ Studio โ generate right here, any language:
FINAL-Bench/POCKET-Image-Studio
๐งฉ Model card:
FINAL-Bench/POCKET-Image-Zimage
๐ The POCKET collection:
https://huggingface.co/collections/FINAL-Bench/pocket-models
SeaWolf-AIย
updated a
collection 4 days ago
SeaWolf-AIย
published a
model 4 days ago
SeaWolf-AIย
updated a
Space 4 days ago
SeaWolf-AIย
published a
Space 4 days ago
SeaWolf-AIย
updated 2
Spaces 4 days ago
SeaWolf-AIย
posted an update 5 days ago
Post
3098
POCKET now speaks Gemma 4 โ a 26B model that loads in every app, and runs on your PC with no GPU
We're adding a Gemma-4 sibling to POCKET: POCKET-26B, built from Google's Gemma-4-26B-A4B (Apache-2.0). Our flagship POCKET-35B is a Qwen-family MoE and needs a recent llama.cpp; POCKET-26B trades a little size for the thing people kept asking for โ it just loads, everywhere, today: Ollama, LM Studio, PocketPal, MLX, any stock llama.cpp. No fork, no bleeding-edge runtime, no CUDA, no cloud.
It's a sparse Mixture-of-Experts (25.2B total, ~4B active per token), so the work per token stays small โ a real 26B that generates on a CPU with no graphics card.
Two things make it stand out:
1) Universal compatibility. Gemma 4 is a standard, widely-supported architecture, so POCKET-26B runs on the tools you already have โ no waiting for your app to add a new model type.
2) Quality that survives compression. Measured GPQA-Diamond (198 q, greedy):
โข Full base: 67.7%
โข POCKET-26B Q4_K_M (17 GB): 67.7% โ lossless
โข POCKET-26B Q2_K (11 GB): 67.2% โ near-lossless, at 11 GB
Live, on a CPU-only box (our demo Space โ POCKET-26B vs Bonsai-27B, same machine, same stock llama.cpp): POCKET-26B โ 19 tok/s vs Bonsai โ 6 tok/s โ about 3ร faster generation, no GPU. (Honest notes: shared CPU box, sequential race; a dedicated machine is faster.)
Where it fits in the family:
โข POCKET-35B (Qwen MoE) โ bigger, top-tier, needs a recent llama.cpp.
โข POCKET-26B (Gemma 4) โ loads in any app, quality-robust when compressed. The demo runs the Q4_K_M build; Q2_K (11 GB) is the smallest footprint. For a true โค8 GB phone, the 5 GB POCKET-KR (Qwen) is still the pick.
Try it and grab it:
๐ฅ๏ธ Live demo (Gemma4-based, answering on a CPU, no GPU): FINAL-Bench/POCKET-26B-CPU
๐ฆ POCKET-26B-GGUF (Q4_K_M 17 GB ยท Q2_K 11 GB): FINAL-Bench/POCKET-26B-GGUF
๐ POCKET collection: https://huggingface.co/collections/FINAL-Bench/pocket-models
We're adding a Gemma-4 sibling to POCKET: POCKET-26B, built from Google's Gemma-4-26B-A4B (Apache-2.0). Our flagship POCKET-35B is a Qwen-family MoE and needs a recent llama.cpp; POCKET-26B trades a little size for the thing people kept asking for โ it just loads, everywhere, today: Ollama, LM Studio, PocketPal, MLX, any stock llama.cpp. No fork, no bleeding-edge runtime, no CUDA, no cloud.
It's a sparse Mixture-of-Experts (25.2B total, ~4B active per token), so the work per token stays small โ a real 26B that generates on a CPU with no graphics card.
Two things make it stand out:
1) Universal compatibility. Gemma 4 is a standard, widely-supported architecture, so POCKET-26B runs on the tools you already have โ no waiting for your app to add a new model type.
2) Quality that survives compression. Measured GPQA-Diamond (198 q, greedy):
โข Full base: 67.7%
โข POCKET-26B Q4_K_M (17 GB): 67.7% โ lossless
โข POCKET-26B Q2_K (11 GB): 67.2% โ near-lossless, at 11 GB
Live, on a CPU-only box (our demo Space โ POCKET-26B vs Bonsai-27B, same machine, same stock llama.cpp): POCKET-26B โ 19 tok/s vs Bonsai โ 6 tok/s โ about 3ร faster generation, no GPU. (Honest notes: shared CPU box, sequential race; a dedicated machine is faster.)
Where it fits in the family:
โข POCKET-35B (Qwen MoE) โ bigger, top-tier, needs a recent llama.cpp.
โข POCKET-26B (Gemma 4) โ loads in any app, quality-robust when compressed. The demo runs the Q4_K_M build; Q2_K (11 GB) is the smallest footprint. For a true โค8 GB phone, the 5 GB POCKET-KR (Qwen) is still the pick.
Try it and grab it:
๐ฅ๏ธ Live demo (Gemma4-based, answering on a CPU, no GPU): FINAL-Bench/POCKET-26B-CPU
๐ฆ POCKET-26B-GGUF (Q4_K_M 17 GB ยท Q2_K 11 GB): FINAL-Bench/POCKET-26B-GGUF
๐ POCKET collection: https://huggingface.co/collections/FINAL-Bench/pocket-models
- 3 replies
SeaWolf-AIย
updated 3
models 5 days ago