BVls

[BVls @BV_ls1]

@AnselLindner Good, it's time to dump all the us debt and watch the country collapse

[BVls @BV_ls1]

@crypto_bitlord7 Meth

[BVls @BV_ls1]

@NVIDIAGeForce #RTXPowersPlay

[Jack 🤖 @JacklouisP]

>be Leopold
>write 165 page essay about the AGI, goes viral, becomes the canonical AI bull case
>name a hedge fund after your essay
>go 4x long every physical object the essay implied
>up 439%, $45bn at peak, main character of AI investing
>july 10, anchor the hynix IPO
>korea's leveraged ETF crowd gets liquidated on top of you
>kospi -40%, memory and semis follow it down
>short adobe, adobe goes up
>july 24, write to investors
>call it the best buying window since early 2025
>PS you can add cash on august 1 pls
>july 27, citadel securities research drops, adds to the FUD
>prices continue to tank
>mfw the margin clerk does not wait until august 1
>goldman calls
>jpmorgan calls
>bank of america calls
>try to raise
>try to borrow
>offer investors the assets directly
>nobody wants it
>only one bid
>ken griffin, hedge fund OG, enters the room
>trading since his harvard dorm in 1987, one of the most profitable funds in history… Citadel
>one shots the whole damn book
>a fund that took two years to build unwinds before lunch
>old dog wins again
>same afternoon the whole book rips 20-30%
>own liquidation was the bottom
>never been more right, own none of it
>time to rebuild I guess

(Meant as entertainment, not information. All power to Leopold — got to respect the hustle and where he got to. I'm sure he'll be back.)

[BVls @BV_ls1]

@CL207 They ran out of money towards the end and had to reuse a lot of material to finish it, that's why it feels different in the end.

It was a sucess and they later made the End of Evangelion as an alternative/fuller ending. And later also made 3 sequel movies

[BVls @BV_ls1]

@CryptoParadyme America is such a goofy place lmao

[BVls @BV_ls1]

@ErikVoorhees Milei is a zionist pig

[BVls @BV_ls1]

@_tm3k https://t.co/tF3gddEW9j

[BVls @BV_ls1]

@trading_axe You forgot that a goalie exists

[BVls @BV_ls1]

@Stoiiic Sir y u jinx it?

[YanXbt @IBuzovskyi]

HERMES AGENT HAS 8 CONFIGS
THAT MOST USERS NEVER CHANGE.
EACH ONE SAVES TOKENS, IMPROVES OUTPUT, OR BOTH.

1. REASONING EFFORT

controls how much thinking per turn.
default: medium.

agent:
reasoning_effort: low

options: none, minimal, low, medium, high, xhigh.
routine cron jobs: low. deep analysis: high.
switch mid-session with /reasoning [level].

lower effort = fewer tokens = cheaper turns.

2. SUB-AGENT MODEL OVERRIDE

sub-agents default to your main model.
a web search sub-agent on Opus is waste.

delegation:
model: "deepseek/deepseek-v4"

simple tasks on cheap models.
parent stays on your premium model.
one config. significant savings.

3. YOLO MODE

skips permission prompts for every action.

approvals:
mode: off

or launch with: hermes --yolo

three modes:
→ manual: approve everything (default)
→ smart: auto-approve low risk, prompt high risk
→ off: skip all prompts

use smart for daily work.
off when you trust the task completely.
never on production systems.

4. MEMORY LIMITS

memory.md caps at 2,200 characters.
user.md caps at 1,375 characters.
after that, the agent drops what it thinks
is least important.

memory:
memory_char_limit: 2200
user_char_limit: 1375

raise these if the agent keeps forgetting
important context.

5. QUICK COMMANDS

two types in config.yaml:

EXEC (runs terminal command, drops output into context):

quick_commands:
git-status:
type: exec
command: "git status && git log --oneline -5"

ALIAS (rename existing commands):

quick_commands:
c:
type: alias
target: compress

/git-status and /c become instant shortcuts.

all settings: Desktop app, Dashboard, or config.yaml.

comment CONFIG and I'll send you
the remaining 3 settings that control
compression behavior and tool output limits.

full 15 levels breakdown in the article 👇

[BVls @BV_ls1]

@RNR_0 Japan might surprise some people i think

[AlexAImaginator @TraffAlex]

🖥️ Best Local LLMs for Consumer GPUs — llama.cpp Guide (June 2026)

What I actually run on consumer hardware right now. Every model below runs via llama.cpp with a simple one-liner — no Docker, no Python env, no cloud.

━━━ 8-16GB VRAM ━━━

🔹 Gemma 4-12B (Google)
• Smartest model in this size class — competes with stuff 2× bigger
• Unsloth's MTP GGUFs: 162 tok/s vs 52 tok/s normal (3× speedup)
• Minimum 8GB VRAM recommended for Q4_K_M quant
• GGUF → https://t.co/VWp818MB3D

🔹 LFM2.5-8B-A1B (LiquidAI)
• Hybrid MoE, only 1B active params — absurdly fast for its size
• Perfect for 8-12GB cards, MacBooks, or anyone on a tight budget
• GGUF → https://t.co/ZbOs4mXJDq

━━━ 16-32GB VRAM ━━━

🔹 Qwen3.6-27B (Qwen)
• Scored 1.00 on tool-efficiency benchmarks — best local agent available
• 40 deterministic tasks, 32k/128k context needle tests — all passed
• GGUF → https://t.co/n7K3sPvliE
• MTP version (faster) → https://t.co/gwdfnJTzcy

🔹 Qwopus3.6-27B-v2 (Jackrong)
• Best quantization of Qwen3.6-27B — topped 5 agent & coding benchmarks (1200 samples)
• If you're running Q4, this is the one to grab
• GGUF → https://t.co/tV1DFqXnOD
• MTP version → https://t.co/PMqz7V5ewv

🔹 Gemma 4-31B QAT (Google/Unsloth)
• QAT variant with MTP draft head: 76-125 tok/s (1.67× speedup)
• Excellent for multi-agent / subagent workflows
• GGUF → https://t.co/FgVsUX0YOB

🔹 Nex-N2-Mini (Nex AGI)
• Post-train of Qwen3.5-35B-A3B — MoE with only 3B active params
• Fits on 16GB+ VRAM, overflow loads from system RAM
• Adaptive thinking saves ~20% tokens with no quality loss
• For deep multi-step reasoning, nothing in this size comes close
• GGUF → https://t.co/oyC522a8Eh

━━━ Quick Picks ━━━

• 16GB all-rounder → Gemma 4-12B with MTP GGUFs
• 32GB all-rounder → Qwen3.6-27B / Qwopus-v2
• Agents & tool use → Qwen3.6-27B or Qwopus Q4
• Deep reasoning → Nex-N2-Mini (MoE, fits 16GB+)
• Tight budget → LFM2.5-8B-A1B
• Cheapest full build: 1× used RTX 3090 (24GB) + rest of PC ≈ $1000-1500

━━━ Setup on Windows ━━━

1. Download llama.cpp → https://t.co/et0J7Swua7 (latest .zip)
2. Extract to any folder (e.g. C:\llama.cpp)
3. Download a .gguf from the links above (Q4_K_M or Q5_K_M for best quality/speed balance)
4. Run one of the commands below depending on your hardware

━━━ Launch Commands ━━━

SINGLE GPU — Standard model (no MTP):

llama-server.exe ^
-m C:\models\Qwen3.6-27B-Q5_K_M.gguf ^
--ctx-size 180000 ^
--flash-attn on ^
--cache-type-k q4_0 ^
--cache-type-v q4_0 ^
--batch-size 1024 --ubatch-size 512 ^
-ngl 100 ^
-np 1 ^
--port 8080 ^
--jinja

SINGLE GPU — MTP model (faster inference):

llama-server.exe ^
-m C:\models\Qwen3.6-27B-MTP-Q5_K_M.gguf ^
--ctx-size 180000 ^
--flash-attn on ^
--cache-type-k q4_0 ^
--cache-type-v q4_0 ^
--batch-size 1024 --ubatch-size 512 ^
--spec-type draft-mtp ^
--spec-draft-n-max 3 ^
-ngl 100 ^
-np 1 ^
--port 8080 ^
--jinja

DUAL GPU — Split across two cards:

llama-server.exe ^
-m C:\models\Qwen3.6-27B-Q5_K_M.gguf ^
--ctx-size 180000 ^
--flash-attn on ^
--cache-type-k q4_0 ^
--cache-type-v q4_0 ^
--batch-size 1024 --ubatch-size 512 ^
-ngl 100 ^
--tensor-split 0.55,0.45 ^
--main-gpu 0 ^
-np 1 ^
--port 8080 ^
--jinja

DUAL GPU + MTP + Vision (multimodal):

llama-server.exe ^
-m C:\models\Qwen3.6-27B-MTP-Q5_K_M.gguf ^
--ctx-size 180000 ^
--flash-attn on ^
--cache-type-k q4_0 ^
--cache-type-v q4_0 ^
--batch-size 1024 --ubatch-size 512 ^
--spec-type draft-mtp ^
--spec-draft-n-max 3 ^
-ngl 100 ^
--tensor-split 0.60,0.40 ^
--main-gpu 0 ^
-np 1 ^
--port 8080 ^
--jinja ^
--mmproj C:\models\mmproj-F16.gguf

━━━ Parameter Breakdown ━━━

-m <path>
Path to your .gguf model file. Change this to wherever you downloaded it.

--ctx-size 180000
Context window in tokens. 180k = huge context for long conversations or big codebases.
Reduce to 32768 or 65536 if you don't need long context — uses less VRAM.

--flash-attn on
Flash Attention — dramatically speeds up inference and reduces VRAM usage.
Works on RTX 30xx/40xx/50xx. Always enable this.

--cache-type-k q4_0 / --cache-type-v q4_0
Quantizes the KV cache (key/value attention cache) to 4-bit.
This is what makes 180k context fit in VRAM. Without it, huge contexts eat all your memory.
Quality impact is minimal — this is a free performance win.

--batch-size 1024 / --ubatch-size 512
batch-size = how many tokens are processed in one forward pass (throughput).
ubatch-size = micro-batch actually sent to the GPU per step.
Higher = faster prompt processing but needs more VRAM.
If you run out of VRAM, lower these (e.g. 512/256).

-ngl 100
Number of layers to offload to GPU. 100 = all layers on GPU (full offload).
This is what you want if the model fits in your VRAM.
If it doesn't fit, reduce this (e.g. -ngl 40) — remaining layers run on CPU/RAM.

--tensor-split 0.55,0.45
How to split model layers across multiple GPUs. Values are ratios.
0.55,0.45 = GPU 0 gets 55% of layers, GPU 1 gets 45%.
Adjust based on your VRAM — give more to the card with more memory.
Example: 0.70,0.30 for a 24GB + 12GB setup.
Not needed for single GPU setups.

--main-gpu 0
Which GPU handles the batch computation (the "orchestrator").
Set to 0 (your primary GPU). The other GPU(s) handle their assigned layers.
Minor performance impact — usually just leave it at 0.

-np 1
Number of parallel slots (concurrent requests). 1 = one user at a time.
Increase to 2-4 if you want multiple clients connected simultaneously.
Each extra slot uses additional VRAM for its own KV cache.

--port 8080
Which port the server listens on. Change if port 8080 is busy.

--jinja
Enables Jinja2 template processing — required for proper chat formatting.
Most modern models expect this. Always include it.

--spec-type draft-mtp
Enables Multi-Token Prediction (MTP) speculative decoding.
Only works with MTP GGUF models (downloaded separately).
The model predicts multiple tokens at once and verifies them — big speed boost.

--spec-draft-n-max 3
How many tokens the MTP draft head proposes per step.
3 is a good default. Higher = potentially faster but more VRAM and may reduce quality.

--mmproj <path>
Path to the multimodal projector file (for vision models).
Enables image understanding — paste screenshots into the web chat.
Only needed if you want vision capabilities. Omit for text-only use.

━━━ Your Hardware → Your Command ━━━

Single GPU (8-24GB VRAM):
Use the "Single GPU" command. Change -m to your model path.
8GB card → Gemma 4-12B Q4 or LFM2.5-8B
12GB card → Gemma 4-12B Q5/Q6
16GB card → Gemma 4-31B QAT Q4 or Nex-N2-Mini
24GB card → Qwen3.6-27B Q4/Q5, Qwopus-v2, Gemma 4-31B QAT Q5/Q6

Dual GPU:
Use the "Dual GPU" command. Adjust --tensor-split based on your VRAM ratio.
24GB + 24GB → --tensor-split 0.50,0.50
24GB + 12GB → --tensor-split 0.70,0.30
24GB + 8GB → --tensor-split 0.75,0.25

Want speed? Use MTP versions of models with the "MTP" commands.

Want vision? Add --mmproj with the projector file from the model's HuggingFace repo.

5. Once running, you get:
• Web chat UI → http://localhost:8080
• OpenAI-compatible API → http://localhost:8080/v1
• Playground → http://localhost:8080/playground

━━━ Why /v1 API Is the Killer Feature ━━━

One local endpoint replaces your entire cloud API bill. The /v1 endpoint is drop-in OpenAI-spec compatible — every tool that speaks OpenAI just works. No custom code, no glue layer.

Works out of the box with:
• IDEs: Cursor, Continue, Windsurf, Cline, Roo Code
• CLI tools: aider, Open Interpreter, OpenCode
• Frameworks: LangChain, LlamaIndex, LiteLLM
• Any OpenAI SDK (Python, Node, Go, Rust)

Why this beats cloud APIs:
• 100% private — code never leaves your machine
• $0 per token — no rate limits, no quotas, no surprise bills
• Works fully offline
• Zero telemetry, no training on your data
• Swap models by dropping in a different .gguf — no app changes needed
• Run 32k–128k context windows without burning money

Good combos:
• Cursor + Qwopus-v2 → near-frontier quality, zero API cost
• Continue + Qwen3.6-27B → best local coding agent
• aider + Gemma 4-12B MTP → 162 tok/s, feels instant
• OpenCode + Nex-N2-Mini → deep reasoning on 16GB

Set any OpenAI-compatible client to your local endpoint:
set OPENAI_API_KEY=sk-dummy (any non-empty string works)
set OPENAI_BASE_URL=http://localhost:8080/v1
# every OpenAI-compatible tool now hits your local GPU

Shoutouts: @0xSero @rS_alonewolf @witcheer @UnslothAI @LottoLabs

[BVls @BV_ls1]

@DipWheeler *laughing in hooligan*

[BVls @BV_ls1]

@NVIDIAGeForce #RTXPowersPlay

[BVls @BV_ls1]

@SMtrades_ "deviation bruh"

[BVls @BV_ls1]

@kingbtc Shit's wild lmao

[BVls @BV_ls1]

@RNR_0 It's just a laptop chip, might as well get 7800xt

[BVls @BV_ls1]

@RunnerXBT :)

[Eugene @ScienceDJX]

This is a thread of the videos they have released from the second batch of UFO files.
1.