Eyal Toledano's banner
Eyal Toledano's profile picture

Eyal Toledano

@EyalToledano • 18,294 subscribers

invented plan mode • leading @usehamster, the ai native workspace for product teams • creator @taskmasterai

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

From the Hamster Labs lab: Introducing Qwen3.8-Flash-Next-REAP-288-MLX-4bit, a 180B-class model running on just 39gb of memory - MLX-native 4-bit 60% smaller than stock q4 - Pruned 512→288 experts via REAP - 91.5% HumanEval (vs 93.9% stock) Hugging Face links below ↓
1:08
EyalToledano's profile picture

From the Hamster Labs lab: Introducing Qwen3.8-Flash-Next-REAP-288-MLX-4bit, a 180B-class model running on just 39gb of memory - MLX-native 4-bit 60% smaller than stock q4 - Pruned 512→288 experts via REAP - 91.5% HumanEval (vs 93.9% stock) Hugging Face links below ↓

Eyal Toledano

46,115 views • 1 month ago

just shipped taskmaster v0.18 🚀 → Claude Code Community provider without API keys → init with IDE-specific profiles for Cursor Claude Code Community @windsurf Cline Visual Studio Code TRAE → cleaner git repos & Python support → PROVIDER_BASE_URL follow + bookmark + dive in 👀👇
8:48
EyalToledano's profile picture

just shipped taskmaster v0.18 🚀 → Claude Code Community provider without API keys → init with IDE-specific profiles for Cursor Claude Code Community @windsurf Cline Visual Studio Code TRAE → cleaner git repos & Python support → PROVIDER_BASE_URL follow + bookmark + dive in 👀👇

Eyal Toledano

85,994 views • 1 year ago

gave codex ai task management powers by letting it call the npm i task-master-ai CLI directly the result is.... beautiful 👀
4:16
EyalToledano's profile picture

gave codex ai task management powers by letting it call the npm i task-master-ai CLI directly the result is.... beautiful 👀

Eyal Toledano

85,662 views • 1 year ago

just shipped taskmaster v0.16 🚀 → .taskmaster folder → bedrock, @azure & Google AI vertex → TASK_MASTER_PROJECT_ROOT & BaseURL → semantic context for add-task → README <> task list sync + welcoming legend Jason Zhou to @taskmasterai follow + bookmark + dive in 👀👇
11:04
EyalToledano's profile picture

just shipped taskmaster v0.16 🚀 → .taskmaster folder → bedrock, @azure & Google AI vertex → TASK_MASTER_PROJECT_ROOT & BaseURL → semantic context for add-task → README <> task list sync + welcoming legend Jason Zhou to @taskmasterai follow + bookmark + dive in 👀👇

Eyal Toledano

69,520 views • 1 year ago

just shipped taskmaster v0.12 🚀 → parse multiple PRDs, smarter breakdowns, easier setup, command improvements,MCP polish +++ → introducing the npm i task-master-ai website, which i have become ossessed with (link below) → 4.5k ⭐ GitHub big upgrades based on your feedback 👇
1:02
EyalToledano's profile picture

just shipped taskmaster v0.12 🚀 → parse multiple PRDs, smarter breakdowns, easier setup, command improvements,MCP polish +++ → introducing the npm i task-master-ai website, which i have become ossessed with (link below) → 4.5k ⭐ GitHub big upgrades based on your feedback 👇

Eyal Toledano

72,354 views • 1 year ago

"which quant should I download?" is a question you may never have to answer again the team Hamster Labs has figured out how to kill it with pMLX. download once at full precision (bf16) and the engine re-fits it to your machine on the fly, based on the job you give it tell it two things: how much context you need, and the slowest speed you'll accept. it reads your mac and picks the quantization plus how many experts stay in ram vs. stream from disk. no need to download a smaller quant or figure out which quant fits your hardware. same model for every use case and the config changes based on what you need I ran this on my own M4 Max and Qwen3.8-Flash-Next splits into two configs. short context, under 32k: full bf16, ~85% of experts in ram, fast at full precision since it fits my ram long context, 64k to 256k: keep ~70% bf16 and stream the rest from SSD at 22 tok/s, or drop to q8 and get 40 tok/s. I pick per task and the model itself never changes. there are many possibilities since I have the ram to spar - if i need speed, Q4 100% resident (74gb ram @ 62 tok/s) - if i need balance, Q8 95% resident (76gb @ 38 tok/s) - if i need accuracy, bf16 70% resident (96gb @ 16 tok/s) given whatever RAM you have (16/32/64/128/256 GB) + your context + your min speed, the engine picks the precision (bf16→q8→q4) and the expert-residency/paging split that fits your box and maximizes quality & speed last thing to optimize is speed. there are so many things we want to power with open models at Hamster and these 180b-300b class models have the potential to play a big role in that
1:47
EyalToledano's profile picture

"which quant should I download?" is a question you may never have to answer again the team Hamster Labs has figured out how to kill it with pMLX. download once at full precision (bf16) and the engine re-fits it to your machine on the fly, based on the job you give it tell it two things: how much context you need, and the slowest speed you'll accept. it reads your mac and picks the quantization plus how many experts stay in ram vs. stream from disk. no need to download a smaller quant or figure out which quant fits your hardware. same model for every use case and the config changes based on what you need I ran this on my own M4 Max and Qwen3.8-Flash-Next splits into two configs. short context, under 32k: full bf16, ~85% of experts in ram, fast at full precision since it fits my ram long context, 64k to 256k: keep ~70% bf16 and stream the rest from SSD at 22 tok/s, or drop to q8 and get 40 tok/s. I pick per task and the model itself never changes. there are many possibilities since I have the ram to spar - if i need speed, Q4 100% resident (74gb ram @ 62 tok/s) - if i need balance, Q8 95% resident (76gb @ 38 tok/s) - if i need accuracy, bf16 70% resident (96gb @ 16 tok/s) given whatever RAM you have (16/32/64/128/256 GB) + your context + your min speed, the engine picks the precision (bf16→q8→q4) and the expert-residency/paging split that fits your box and maximizes quality & speed last thing to optimize is speed. there are so many things we want to power with open models at Hamster and these 180b-300b class models have the potential to play a big role in that

Eyal Toledano

10,743 views • 1 month ago

Qwen3.8-Flash-Next now fits on a 48gb macbook air Got q4 running on MLX using only 39gb of memory and decoding at 28 tok/s 🔥 Also q8 running on just 50gb of memory I stacked two tricks so far: 1. REAP pruning cut the expert pool from 68gb to 35gb 2. the 51b n-gram table now lives on the ssd instead of ram My patch memmaps the shards and reads ~100 bytes per lookup straight off disk, dequantized on cpu and verified bit-exact against the gpu path Qwen3.8-Flash-Next at 288 experts with its PLE table on nvme loads in 6 seconds, 39gb resident, 28 tok/s decode, 600 tok/s prefill. Logits identical to the ram-resident version in every way 97gb stock Q4 down to 68gb if pruned to 288 experts down to 39gb if pruned to 288 experts with the table on disk humaneval scoring 91.5% with 288 experts vs. 93.9% for stock I'm not done. next: 1. MTP drafter for speculative decode 2. n-gram lookup drafter both are built, benchmarking them now
2:27
EyalToledano's profile picture

Qwen3.8-Flash-Next now fits on a 48gb macbook air Got q4 running on MLX using only 39gb of memory and decoding at 28 tok/s 🔥 Also q8 running on just 50gb of memory I stacked two tricks so far: 1. REAP pruning cut the expert pool from 68gb to 35gb 2. the 51b n-gram table now lives on the ssd instead of ram My patch memmaps the shards and reads ~100 bytes per lookup straight off disk, dequantized on cpu and verified bit-exact against the gpu path Qwen3.8-Flash-Next at 288 experts with its PLE table on nvme loads in 6 seconds, 39gb resident, 28 tok/s decode, 600 tok/s prefill. Logits identical to the ram-resident version in every way 97gb stock Q4 down to 68gb if pruned to 288 experts down to 39gb if pruned to 288 experts with the table on disk humaneval scoring 91.5% with 288 experts vs. 93.9% for stock I'm not done. next: 1. MTP drafter for speculative decode 2. n-gram lookup drafter both are built, benchmarking them now

Eyal Toledano

10,538 views • 1 month ago

we've shipped taskmaster v0.20 🚀 → mcp sampling support (zero api keys) → Gemini CLI integration & provider → advanced Claude Code Community rules → language override → Grok 4 support → Groq Inc support → parse-prd auto-selects task number & more follow + bookmark + vibe 👀👇
17:39
EyalToledano's profile picture

we've shipped taskmaster v0.20 🚀 → mcp sampling support (zero api keys) → Gemini CLI integration & provider → advanced Claude Code Community rules → language override → Grok 4 support → Groq Inc support → parse-prd auto-selects task number & more follow + bookmark + vibe 👀👇

Eyal Toledano

48,608 views • 1 year ago

we've shipped taskmaster v0.23 🚀 → official npm i task-master-ai Visual Studio Code extension → manage your taskmaster workflow visually → introducing scope-up & scope-down tools → dozens of QOL improvements & fixes → we're hiring 🐹 follow + retweet + bookmark 👀👇
9:07
EyalToledano's profile picture

we've shipped taskmaster v0.23 🚀 → official npm i task-master-ai Visual Studio Code extension → manage your taskmaster workflow visually → introducing scope-up & scope-down tools → dozens of QOL improvements & fixes → we're hiring 🐹 follow + retweet + bookmark 👀👇

Eyal Toledano

43,375 views • 1 year ago

just recorded a 10min video that shows how to use @taskmasterai on existing projects you'll learn how to: - weaponize Cursor for code context - quickly create PRDs for refactors/improvements - create, research & expand the new tasks bookmark, retweet & vibe away friends
9:58
EyalToledano's profile picture

just recorded a 10min video that shows how to use @taskmasterai on existing projects you'll learn how to: - weaponize Cursor for code context - quickly create PRDs for refactors/improvements - create, research & expand the new tasks bookmark, retweet & vibe away friends

Eyal Toledano

43,716 views • 1 year ago

we've shipped huge features in taskmaster v0.37 🚀 → real-time PRDs, team plans, synced tasks 🐹 → GPT-5, LM Studio, Z.AI GLM → Claude plugin + AI SDK v5 → smaller MCP tool footprint → redesigned init ux → enterprise proxy + more follow + retweet + bookmark 👀👇
13:22
EyalToledano's profile picture

we've shipped huge features in taskmaster v0.37 🚀 → real-time PRDs, team plans, synced tasks 🐹 → GPT-5, LM Studio, Z.AI GLM → Claude plugin + AI SDK v5 → smaller MCP tool footprint → redesigned init ux → enterprise proxy + more follow + retweet + bookmark 👀👇

Eyal Toledano

29,260 views • 10 months ago

just shipped taskmaster v0.17 🚀 → multi-context task management via tagged lists → `research` MCP tool with interactive CLI → get-task/show upgrades & batch ops → --append for update-task → save research to docs → multi-status filters follow + bookmark + dive in 👀👇
22:27
EyalToledano's profile picture

just shipped taskmaster v0.17 🚀 → multi-context task management via tagged lists → `research` MCP tool with interactive CLI → get-task/show upgrades & batch ops → --append for update-task → save research to docs → multi-status filters follow + bookmark + dive in 👀👇

Eyal Toledano

37,012 views • 1 year ago

we've shipped taskmaster v0.24 🚀 → Claude subagent support → code-aware task generation → orchestrator: hands-off task management → executor: autonomous parallel development → checker: testing + validating production → GPT-5 support follow + retweet + bookmark 👀👇
16:50
EyalToledano's profile picture

we've shipped taskmaster v0.24 🚀 → Claude subagent support → code-aware task generation → orchestrator: hands-off task management → executor: autonomous parallel development → checker: testing + validating production → GPT-5 support follow + retweet + bookmark 👀👇

Eyal Toledano

29,873 views • 1 year ago

recorded a 42 min video explaining what npm i task-master-ai is and how to get started with it. didn't get to write code yet so part 2 is coming i have no idea if you'll find this useful, but if you do, lmk and i'll continue and possibly turn it into a series open to all feedback!
42:41
EyalToledano's profile picture

recorded a 42 min video explaining what npm i task-master-ai is and how to get started with it. didn't get to write code yet so part 2 is coming i have no idea if you'll find this useful, but if you do, lmk and i'll continue and possibly turn it into a series open to all feedback!

Eyal Toledano

25,980 views • 1 year ago

just shipped taskmaster v0.15 🚀 → add-task is now context-aware 🔥 → research flag for parse-prd → new move command → analyze-complexity of specific tasks → add tasks without a PRD → ollama improved → celebrating 10k ⭐️ on GitHub +++ follow + bookmark + dive in 👀👇
15:41
EyalToledano's profile picture

just shipped taskmaster v0.15 🚀 → add-task is now context-aware 🔥 → research flag for parse-prd → new move command → analyze-complexity of specific tasks → add tasks without a PRD → ollama improved → celebrating 10k ⭐️ on GitHub +++ follow + bookmark + dive in 👀👇

Eyal Toledano

15,474 views • 1 year ago

we've shipped taskmaster v0.22 🚀 → Kiro hooks like: → hook for task tracker → hook to link tasks to commits → set task to complete when tests pass → gemini cli upgrade → better tag handling → token limit improvements follow + retweet + bookmark 👀👇
16:25
EyalToledano's profile picture

we've shipped taskmaster v0.22 🚀 → Kiro hooks like: → hook for task tracker → hook to link tasks to commits → set task to complete when tests pass → gemini cli upgrade → better tag handling → token limit improvements follow + retweet + bookmark 👀👇

Eyal Toledano

14,019 views • 1 year ago

trying a TDD + git workflow npm i task-master-ai → test-driven development → github branch for each task → commit + test each subtask once done → push PR when task is feature complete → full code coverage → nearly autopilot will polish and ship as rules first then as a feature
5:41
EyalToledano's profile picture

trying a TDD + git workflow npm i task-master-ai → test-driven development → github branch for each task → commit + test each subtask once done → push PR when task is feature complete → full code coverage → nearly autopilot will polish and ship as rules first then as a feature

Eyal Toledano

14,586 views • 1 year ago