POCKET-MODELs
Collection
7 items • Updated • 14
Young Sik Hong PRO
RICHARDYHONG
AI & ML interests
None yet
Recent Activity
reacted to SeaWolf-AI's post with 🧠 about 11 hours ago
POCKET now speaks Gemma 4 — 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 — 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 — 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 — no waiting for your app to add a new model type.
2) Quality that survives compression. Measured GPQA-Diamond (198 q, greedy):
• Full base: 67.7%
• POCKET-26B Q4_K_M (17 GB): 67.7% — lossless
• POCKET-26B Q2_K (11 GB): 67.2% — near-lossless, at 11 GB
Live, on a CPU-only box (our demo Space — POCKET-26B vs Bonsai-27B, same machine, same stock llama.cpp): POCKET-26B ≈ 19 tok/s vs Bonsai ≈ 6 tok/s → about 3× faster generation, no GPU. (Honest notes: shared CPU box, sequential race; a dedicated machine is faster.)
Where it fits in the family:
• POCKET-35B (Qwen MoE) — bigger, top-tier, needs a recent llama.cpp.
• POCKET-26B (Gemma 4) — 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 ≤8 GB phone, the 5 GB POCKET-KR (Qwen) is still the pick.
Try it and grab it:
🖥️ Live demo (Gemma4-based, answering on a CPU, no GPU): https://huggingface.co/spaces/FINAL-Bench/POCKET-26B-CPU
📦 POCKET-26B-GGUF (Q4_K_M 17 GB · Q2_K 11 GB): https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF
📚 POCKET collection: https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6 reacted to SeaWolf-AI's post with ❤️ about 11 hours ago
POCKET now speaks Gemma 4 — 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 — 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 — 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 — no waiting for your app to add a new model type.
2) Quality that survives compression. Measured GPQA-Diamond (198 q, greedy):
• Full base: 67.7%
• POCKET-26B Q4_K_M (17 GB): 67.7% — lossless
• POCKET-26B Q2_K (11 GB): 67.2% — near-lossless, at 11 GB
Live, on a CPU-only box (our demo Space — POCKET-26B vs Bonsai-27B, same machine, same stock llama.cpp): POCKET-26B ≈ 19 tok/s vs Bonsai ≈ 6 tok/s → about 3× faster generation, no GPU. (Honest notes: shared CPU box, sequential race; a dedicated machine is faster.)
Where it fits in the family:
• POCKET-35B (Qwen MoE) — bigger, top-tier, needs a recent llama.cpp.
• POCKET-26B (Gemma 4) — 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 ≤8 GB phone, the 5 GB POCKET-KR (Qwen) is still the pick.
Try it and grab it:
🖥️ Live demo (Gemma4-based, answering on a CPU, no GPU): https://huggingface.co/spaces/FINAL-Bench/POCKET-26B-CPU
📦 POCKET-26B-GGUF (Q4_K_M 17 GB · Q2_K 11 GB): https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF
📚 POCKET collection: https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6 reacted to SeaWolf-AI's post with 👍 about 11 hours ago
POCKET now speaks Gemma 4 — 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 — 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 — 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 — no waiting for your app to add a new model type.
2) Quality that survives compression. Measured GPQA-Diamond (198 q, greedy):
• Full base: 67.7%
• POCKET-26B Q4_K_M (17 GB): 67.7% — lossless
• POCKET-26B Q2_K (11 GB): 67.2% — near-lossless, at 11 GB
Live, on a CPU-only box (our demo Space — POCKET-26B vs Bonsai-27B, same machine, same stock llama.cpp): POCKET-26B ≈ 19 tok/s vs Bonsai ≈ 6 tok/s → about 3× faster generation, no GPU. (Honest notes: shared CPU box, sequential race; a dedicated machine is faster.)
Where it fits in the family:
• POCKET-35B (Qwen MoE) — bigger, top-tier, needs a recent llama.cpp.
• POCKET-26B (Gemma 4) — 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 ≤8 GB phone, the 5 GB POCKET-KR (Qwen) is still the pick.
Try it and grab it:
🖥️ Live demo (Gemma4-based, answering on a CPU, no GPU): https://huggingface.co/spaces/FINAL-Bench/POCKET-26B-CPU
📦 POCKET-26B-GGUF (Q4_K_M 17 GB · Q2_K 11 GB): https://huggingface.co/FINAL-Bench/POCKET-26B-GGUF
📚 POCKET collection: https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6Organizations
None yet
upvoted a collection 3 days ago
upvoted a collection 6 days ago
upvoted an article 6 days ago
Article
Aether-7B-5Attn: A 100% Open-Source Sovereign Foundation Model — and a Controlled Experiment in Heterogeneous Attention
FINAL-Bench
• • 21 upvoted an article 10 days ago
Article
VKUE: No GPU? Runs Anyway — a 34.7B Reasoner on a Laptop and on Bare CPU
FINAL-Bench
• • 17 upvoted an article 21 days ago
Article
Quantum Cryptanalysis on Real Hardware: Pushing Symmetric-Structure Key Recovery Beyond the Published Frontier
FINAL-Bench
• • 15 upvoted an article 25 days ago
Article
Does Your LLM Know *When It's About to Be Wrong*?
ginigen-ai
• • 21 upvoted an article 26 days ago
Article
Chitos: From Detection to Proof — An Autonomous Security AI That Actually Exploits
FINAL-Bench
• • 19 upvoted a paper 2 months ago
upvoted 2
articles 3 months ago
Article
Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion
FINAL-Bench
• • 13 Article
"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"
FINAL-Bench
• • 16 upvoted a collection 3 months ago
upvoted 3
articles 4 months ago
Article
Darwin V6: Diagnostic-Guided Evolutionary Model Merging
FINAL-Bench
• • 12 Article
"The Child That Surpassed Both Parents Through MRI-Guided Evolutionary Merge"
FINAL-Bench
• • 15 Article
Introducing WM Bench: A Benchmark for Cognitive Intelligence in World Models
FINAL-Bench
• • 13