Cheapest way to run Mistral Large 4 (Le Chonk)
Quick answer
At 4-bit with an 8K-token conversation, Mistral Large 4 (Le Chonk) needs about 635.5 GB. The cheapest rental big enough is 4× B200 SXM6 on Lambda at $31.16 an hour.
| Option | What you need | Cost | Notes |
|---|---|---|---|
| Your own GPU | Doesn't fit any single consumer card in our list (largest 32 GB) at 4-bit with 8K context | – | – |
| Rent a GPU | 4× B200 SXM6 (720 GB total) on Lambda, On-demand instance | $31.16 per hour ($7.79 per GPU) | Pay only while it runs. Price checked 2026-11-09 |
Fit rule: the Q4_K_M file (or the highest precision that fits) plus an 8K-token FP16 KV cache under 90% of memory, same as the calculator. Sizes and sources: Mistral Large 4 (Le Chonk) VRAM page. Rental prices: GPU prices (checked 2026-11-09). Hourly and per-token prices measure different things, so which is cheaper depends on how much you use it.
Links marked Referral link, Affiliate partner or Amazon affiliate link may earn us credit or a commission at no cost to you. Disclosure.
Precision ladder: what each quant costs
| Precision | Needs at 8K | Smallest consumer GPU | Smallest Mac | Cheapest single-GPU rental | Cheapest rental overall (any GPU count) |
|---|---|---|---|---|---|
| 16-bit (FP16/BF16) | 2099.5 GB | none (max 32 GB) | none in our Mac list | none big enough in our price data | none big enough in our price data |
| 8-bit (Q8_0) | 1115.8 GB | none (max 32 GB) | none in our Mac list | none big enough in our price data | 8× B200 SXM6 (1440 GB) on Lambda, $61.52/hr |
| 4-bit (Q4_K_M) | 635.5 GB | none (max 32 GB) | none in our Mac list | none big enough in our price data | 4× B200 SXM6 (720 GB) on Lambda, $31.16/hr |
Every row names its precision, Mac rows included (Macs share unified memory with the system, so the same 90% rule applies). Single-GPU and multi-GPU rentals are listed separately: a multi-GPU rental needs software that splits the model across cards (llama.cpp, vLLM tensor parallel). Prices checked 2026-11-09.
How context length changes the bill (4-bit)
| Context | Needs | Cheapest rental overall |
|---|---|---|
| 8K tokens | 635.5 GB | 4× B200 SXM6 (720 GB) on Lambda, $31.16/hr |
| 32K tokens | 637.5 GB | 4× B200 SXM6 (720 GB) on Lambda, $31.16/hr |
| 128K tokens | 645.8 GB | 4× B200 SXM6 (720 GB) on Lambda, $31.16/hr |
What $100 of rental buys you
We list no GPU purchase prices (they change daily and we cannot check them), so this page does not compare renting with buying. At the cheapest rental that fits (4× B200 SXM6 (720 GB) on Lambda, $31.16/hr), $100 of rental buys about 3 hours of running Mistral Large 4 (Le Chonk) at 4-bit with 8K context. Electricity, storage and setup time are not counted.
Fit quirks for this model
- Mixture-of-experts: about 49.0B parameters are active per token, but every expert must still be in memory, so VRAM follows the total size, not the active size.
- Our estimate from config.json (MLA latent cache 576 values x 63 unique KV layers + 128-dim indexer x 44 layers, BF16). Mistral does not publish a figure.
- Maximum context is 1,048,576 tokens; longer settings are capped.
Model data checked 2026-10-31; rental prices checked 2026-11-09. For file sizes, sources and the full fit table see the Mistral Large 4 (Le Chonk) VRAM requirements page; this page is only about cost.
Get fit alerts for your GPU
Join the fit-alerts waitlist
Alerts are not running yet. Join the waitlist and pick your card once; when alerts launch we will email you once to confirm, and only after you confirm will you get the first alerts. Unsubscribe any time.
More: all cheapest-way pages · cheapest GPU rental by VRAM · Ask VRAMNeeded · Scan my GPU