unsloth/Kimi-K3
Image-Text-to-Text • 2.8T • Updated • 410 • 131
Yune Leou
leouon
AI & ML interests
None yet
Recent Activity
liked a model about 8 hours ago
unsloth/Kimi-K3 liked a model about 11 hours ago
moonshotai/Kimi-K3 reacted to SeaWolf-AI's post with 🔥 3 days 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-modelsOrganizations
None yet
liked a
model about 8 hours ago
liked a
model about 11 hours ago
reacted to SeaWolf-AI's post with 🔥 3 days ago
Post
3049
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): FINAL-Bench/POCKET-26B-CPU
📦 POCKET-26B-GGUF (Q4_K_M 17 GB · Q2_K 11 GB): FINAL-Bench/POCKET-26B-GGUF
📚 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 — 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): FINAL-Bench/POCKET-26B-CPU
📦 POCKET-26B-GGUF (Q4_K_M 17 GB · Q2_K 11 GB): FINAL-Bench/POCKET-26B-GGUF
📚 POCKET collection: https://huggingface.co/collections/FINAL-Bench/pocket-models
- 3 replies
liked a
model 3 days ago
liked a
model 6 days ago
liked 2
models 7 days ago
reacted to danielhanchen's post with 🚀❤️🔥 8 days ago
Post
4379
Introducing Unsloth for AMD 🚀
You can now train & run LLMs on your AMD hardware
• We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
• Works on Windows, WSL, Linux
• Train Qwen, Gemma on just 3GB VRAM
GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd
You can now train & run LLMs on your AMD hardware
• We collaborated with AMD to enable you to train & run 500+ models on AMD GPUs
• Works on Windows, WSL, Linux
• Train Qwen, Gemma on just 3GB VRAM
GitHub: https://github.com/unslothai/unsloth
Blog + Guide: https://unsloth.ai/docs/basics/amd
- 3 replies
liked 2
models 8 days ago
liked 2
models 9 days ago
reacted to danielhanchen's post with 🚀 9 days ago
Post
5587
Gemma 4 is now faster and much more accurate! 🚀
Google made huge improvements to tool-calling and chat accuracy, reliability + speed.
To get fixes, re-download our updated GGUF, MLX, NVFP4 quants!
Unsloth quants: https://huggingface.co/collections/unsloth/gemma-4
Gemma 4 Guide: https://unsloth.ai/docs/models/gemma-4
Google made huge improvements to tool-calling and chat accuracy, reliability + speed.
To get fixes, re-download our updated GGUF, MLX, NVFP4 quants!
Unsloth quants: https://huggingface.co/collections/unsloth/gemma-4
Gemma 4 Guide: https://unsloth.ai/docs/models/gemma-4
- 8 replies
reacted to Banaxi-Tech's post with 👍 13 days ago
Post
3809
We are announcing 3 more models in our BananaMind 2 Family of models!
BananaMind 2 Nano, a small 10M parameter model, fits on your Pentium 4
BananaMind 2 Medium, our medium model, 50M parameters
BananaMind 2 MoE, 25M parameters, 2M active per tokens as fast as a 2M.
Because of this our release dates have changed a bit our currently estimates are:
BananaMind 2 MoE July 16-18
BananaMind 2 Nano July 18-20
BananaMind 2 Medium July 24-28
BananaMind 2 Pro August 10-16
Keep in mind these dates are estimates and we don't have a speed number currently, we will post for details going forward!
BananaMind 2 Nano, a small 10M parameter model, fits on your Pentium 4
BananaMind 2 Medium, our medium model, 50M parameters
BananaMind 2 MoE, 25M parameters, 2M active per tokens as fast as a 2M.
Because of this our release dates have changed a bit our currently estimates are:
BananaMind 2 MoE July 16-18
BananaMind 2 Nano July 18-20
BananaMind 2 Medium July 24-28
BananaMind 2 Pro August 10-16
Keep in mind these dates are estimates and we don't have a speed number currently, we will post for details going forward!
liked 4
models 13 days ago
FadedRedStar/gemma-4-E2B-it-qat-q4_0-heretic-GGUF
Image-Text-to-Text • 5B • Updated • 4.17k • 3
Danny-Dasilva/Ternary-Bonsai-27B-antidoom-DSpark
Text Generation • 27B • Updated • 3.47k • 8
prism-ml/Bonsai-27B-gguf
Text Generation • 4B • Updated • 2.34M • 662
redhunt07/DeepSeek-V4-Flash-DSpark-Abliterated-COMBINED-Q2-DS4.gguf
Text Generation • Updated • 1