Can the Arc B570 run Mistral 7B Instruct v0.3?
Fits comfortably at Q4_K_M.
Mistral 7B Instruct v0.3 is 7.25B parameters. At Q4_K_M the weights are about 4.1 GiB; with the 1.5 GiB runtime reserve that is 5.6 GiB against the card's 10GB, leaving about 4.4 GiB for context.
All three quants
10GB card| Quant | Weights | With reserve | Verdict | Headroom |
|---|---|---|---|---|
| Q4_K_Mthe everyday quant | 4.1 GiB | 5.6 GiB | Fits comfortably | 4.4 GiB |
| Q8_0near-lossless | 7.2 GiB | 8.7 GiB | Fits, tight on context | 1.3 GiB |
| FP16full weights | 13.5 GiB | 15.0 GiB | Only with CPU offload | short 5.0 GiB |
Verdict rules: fits comfortably when weights plus reserve sit within 85% of VRAM; tight when they fit with little left for context; CPU offload when they exceed VRAM by up to 2x (runs, slowly, with layers in system RAM); no beyond that. The KV cache per token depends on the model's architecture and is not modelled here.
The numbers for this pairing
At Q4_K_M the weights take about 4.1 GiB; with the 1.5 GiB we set aside for the runtime that is 5.6 of the card's 10 GB, leaving about 4.4 GB for the context cache.
The highest-quality version that fits entirely in memory is Q8_0.
This is the cheapest card on our list that runs it comfortably at Q4, at about $260.
At about $260, this card costs roughly $26 per GB of VRAM.
Running it at its full 150 W board power for 4 hours a day would use about 18 kWh a month, about $3.31 at the US average residential rate of 18.4 cents per kWh (2026-05); real use sits below that ceiling.
Prices are the lowest current listings our tracker saw on Oct 7, 2026, since averages include premium variants; launch prices are marked where we have no listing.
Good match. Get the card.
The Arc B570 clears Mistral 7B Instruct v0.3 at Q4_K_M and at Q8_0. Live listings below; this page was rebuilt 2026-10-07.
Amazon links may earn us a commission. Prices move daily; the links open live listings.
About the model
Mistral 7B Instruct v0.3 by Mistral AI: 32,768-token native context, text, released 2024 under the Apache-2.0. Model card →