LIVE TELEMETRYGPT-5$1.25 / $10.00Sonnet 5.5$2.00 / $10.00Gemini 3.8$0.75 / $3.75DS V4.1$0.15 / $0.60RTX 50901,792 GB/sM4 Max546 GB/sUS Avg$0.182/kWh
TELEMETRY CONSOLE NAVIGATION

Guncelkal Telemetry Index

Search VRAM specs, API costs, or Dev tools

AI & LLM EconomicsQ4_K_M • 21.6 GB Total

Can an RTX 4090 Run Qwen 2.5 / R1 32B Locally?

Exact Q4_K_M and IQ3_XS VRAM sizing, KV-cache limits, and tokens/sec on an NVIDIA RTX 4090 24 GB.

Hardware & Model Configuration

8,192 tokens
1 stream
64 GB
KV Cache Precision:
CLI LAUNCH SNIPPET
OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 \
  ollama run qwen2.5-coder:32b-instruct-q4_k_m --ctx-size 8192
Total Required
21.6 GB
Safe cap: 22.8 GB
Est. Speed
32.9 tok/s
Decode bandwidth bound
KV Cache
1 GB
Q8_0 @ 8K ctx
Max Context Fit
18,022
Tokens before spill
VRAM ALLOCATION & KV-CACHE MAP21.6 GB / 22.8 GB Usable
Safe Pool (22.8 GB)Physical 24 GB
Weights: 19.7 GB KV Cache: 1 GB Runtime: 0.9 GB
Status: Tight Fit (Near Memory Ceiling — Cap Context)

All 7 GGUF / Quantization Tiers on NVIDIA RTX 4090 (24 GB)

QuantizationMemory NeededSpeed Est.Placement
FP16 / BF16 (16-bit)Reference Lossless66.9 GB1 tok/sRAM Offload
Q8_0 (8-bit)Near-Lossless36.43 GB2.5 tok/sRAM Offload
Q6_K (6-bit K-Quant)Studio Fidelity28.55 GB3.8 tok/sRAM Offload
Q5_K_M (5-bit Medium)Minimal Loss25.06 GB4.8 tok/sRAM Offload
Q4_K_M (4-bit Sweet Spot)Recommended Default21.6 GB32.9 tok/sPure GPU VRAM
IQ3_XS (3.3-bit I-Quant)Noticeable Degradation15.71 GB52 tok/sPure GPU VRAM
IQ2_XXS (2.1-bit Extreme)Emergency Fit Only10.84 GB79.9 tok/sPure GPU VRAM

All 11 Open-Weight LLMs Ranked for NVIDIA RTX 4090 (24 GB) (Click Row to Switch)

ModelBest Pure-VRAM QuantMemoryEst. Speed
Llama 3.1 8B InstructUltra-fast RAG extraction, IDE autocomplete & classificationFP1617.46 GB45 tok/s
Qwen 2.5 Coder 14BMid-tier local VS Code copilot balancing speed & repo accuracyQ8_017.27 GB46.1 tok/s
Mistral Small 24BClean instruction following on 24 GB single-GPU workstationsQ6_K21.21 GB33 tok/s
Gemma 2 / 3 27BMultilingual & editorial writing in single 24–32 GB GPUsQ5_K_M21.72 GB33.3 tok/s
Qwen 2.5 32B / DeepSeek-R1 32BGold-standard local coding & reasoning on RTX 3090/4090/5090 & 48GB MacsQ4_K_M21.6 GB32.9 tok/s
Mixtral 8x7B MoE (46.7B Total)Sparse Mixture-of-Experts: needs 47B RAM footprint, computes at 13B speedIQ3_XS21.55 GB117.5 tok/s
Llama 3.3 70B / DeepSeek-R1 70BGPT-4 class private local reasoning for 48 GB–128 GB rigsIQ2_XXS21.87 GB33.3 tok/s
DeepSeek R1 671B MoE (Full Frontier)Cluster or Mac Studio Ultra / dual EPYC server deployment (37B active per token)Needs Offload / Cluster408.95 GBOOM
Qwen3-30B-A3B (MoE — 3.3B Active)Ultra-fast 30B Sparse MoE decoding at 3.3B speed; effortless fit on 24 GB cardsQ4_K_M19.77 GB352.8 tok/s
Qwen3-32B (Dense Dual-Thinking)2026 dense local reasoning & coding benchmark with dual thinking/non-thinking toggleQ4_K_M21.78 GB32.6 tok/s
Llama 4 Scout 109B (MoE — 17B Active)Multimodal 109B MoE (17B active) built for 64–128 GB Macs, Dual-3090, or H100 podsNeeds Offload / Cluster68.03 GB6 tok/s

Telemetry Methodology & Benchmark Sources

Read full equations →

Pre-configured telemetry for Qwen 2.5 32B / DeepSeek-R1 32B (Q4_K_M) on NVIDIA RTX 4090 (24 GB). Requires 21.6 GB (19.7 GB weights + 1 GB Q8 KV cache) against 22.8 GB usable pool for ~32.9 tok/s decode.

Primary Technical & US Grid Benchmarks

  • llama.cpp GGUF Model Sizing
  • Apple Metal / CUDA Wired VRAM Limits
  • GQA Attention Context Scaling Spec

Engineering & Pricing FAQ

Can NVIDIA RTX 4090 (24 GB) run Qwen 2.5 32B / DeepSeek-R1 32B without CPU RAM offload?
Fits comfortably at Q4_K_M (~21 GB total with 8K Q8 KV cache) at ~48–60 tok/s. At Q4_K_M with 8K context, total required memory is 21.6 GB compared to 22.8 GB safe usable GPU VRAM.
What max context length fits inside NVIDIA RTX 4090 (24 GB)?
At Q4_K_M quantization on single-stream inference, safe KV-cache capacity supports up to 18,022 tokens before spilling into host system RAM.

Continue in Console Workflow

AI & LLM Economics

Cloud vs. Rig TCO

Plot cumulative 36-month API spending against hourly RunPod/H100 rentals and owned RTX/Mac hardware with electricity and resale value.

Open Workbench
Hardware & Power

kWh Power Cost Lab

Calculate daily, monthly, and annual kWh bills using 80+ PSU efficiency, duty cycle, optional AC cooling load, and 50 US state EIA rates.

Open Workbench
Hardware & Power

PSU Wattage & Spike

Combine dual-GPU draw, CPU peak boost, NVMe arrays, and ATX 3.1 transient spikes to hit the 50–70% PSU efficiency sweet spot.

Open Workbench