Models › Mistral Medium 3.5 128B

Can I run Mistral Medium 3.5 128B in Australia?

Yes. The cheapest hardware we track that holds Mistral Medium 3.5 128B at Q4_K_M with an 8k context is the Minisforum MS-S1 Max (Ryzen AI Max+ 395) 128GB at A$5,719 (Minisforum AU, checked 20 Oct 2026, 7:44 am AEST). Expect roughly 2 tokens/sec (estimate).

Mistral · released 31 Mar 2026 · 0.1M HF downloads (last 30 days)

127.7Btotal parameters (dense)
88layers (88 full-attention)
2.95 GBKV cache @ 8k · 8 KV heads × 128 dim
Model card ↗config.json · source of counts

GGUF builds: unsloth · bartowski

Memory needed by quantisation (8k context)

QuantWeightsTotal neededCheapest hardware that fits
Q4_K_M
77.4 GB
81.4 GB
Q5_K_M
90.8 GB
94.8 GB
Q6_K
104.7 GB
108.7 GB
Q8_0
135.7 GB
139.6 GB
F16
255.4 GB
259.4 GB
nothing we track (with a price)

All hardware that fits at Q4_K_M

HardwareNeeds / usableEst. tok/sPriceRetailer link
81.4 / 96.0 GB fits
2 estimate
A$5,719
Minisforum AU
checked 20 Oct 2026, 7:44 am AEST
81.4 / 96.0 GB fits
2 estimate
A$8,999
Mwave · not in stock online
checked 20 Oct 2026, 7:44 am AEST
81.4 / 96.0 GB fits
3 estimate
A$8,999
Mwave
checked 20 Oct 2026, 7:44 am AEST
81.4 / 96.0 GB fits
3 estimate
A$9,649
Microsoft Store AU · stale
checked 19 Oct 2026, 8:18 pm AEST
81.4 / 192.0 GB fits
9 estimate
A$11,449
Apple AU
checked 20 Oct 2026, 7:44 am AEST
81.4 / 95.5 GB fits
13 estimate
A$27,599
Scorptec
checked 20 Oct 2026, 7:42 am AEST
81.4 / 96.0 GB fits
2 estimate
price unavailable

The tok/s figures are bandwidth-based estimates for this model. Where a device has a measured benchmark, the estimate is calibrated to that run. They are not measurements. Methodology.

Graphics card + system RAM (partial layer offload)

Dense models can split layers between GPU and system RAM, but every token reads all the weights, so the RAM part is slow. All figures below are estimates (Q4_K_M, 8k context, dual-channel DDR5-5600). How we estimate.

Graphics cardCard priceGPU only+ 32GB RAM+ 64GB RAM+ 128GB RAM
A$419
no
no
no
fits
71 GB in RAM · ~1 tok/s
A$539
no
no
no
fits
71 GB in RAM · ~1 tok/s
A$699
no
no
no
fits
67 GB in RAM · ~1 tok/s
A$1,099
no
no
no
fits
67 GB in RAM · ~1 tok/s
A$1,099
no
no
no
fits
67 GB in RAM · ~1 tok/s
A$1,169
no
no
no
fits
67 GB in RAM · ~1 tok/s
A$1,249
no
no
no
fits
71 GB in RAM · ~1 tok/s
A$1,699
no
no
no
fits
67 GB in RAM · ~1 tok/s
A$2,299
no
no
no
fits
67 GB in RAM · ~1 tok/s
A$2,299
no
no
tight
53 GB in RAM · ~1 tok/s
fits
53 GB in RAM · ~1 tok/s
A$3,599
no
no
no
fits
60 GB in RAM · ~1 tok/s
A$10,999
no
no
tight
53 GB in RAM · ~1 tok/s
fits
53 GB in RAM · ~1 tok/s
A$27,599
fits
~13 tok/s
fits in VRAM
fits in VRAM
fits in VRAM
n/a
no
no
no
fits
67 GB in RAM · ~1 tok/s
n/a
no
no
no
fits
60 GB in RAM · ~1 tok/s
n/a
no
no
no
fits
60 GB in RAM · ~1 tok/s
n/a
no
no
no
fits
60 GB in RAM · ~1 tok/s

DDR5 kit prices today: 32GB: A$610 (Mwave, checked 20 Oct 2026, 7:44 am AEST) · 64GB: A$1,499 (Mwave, checked 20 Oct 2026, 7:44 am AEST) · 128GB: A$2,511 (Mwave, not in stock online, checked 20 Oct 2026, 7:44 am AEST). Card + kit only; the rest of the PC isn't included. RAM-offload speeds are estimates and can be optimistic, so check community results below.

Community measured

No reader results yet. Be the first to submit one →

Try other quantisations and context lengths in the Can I run it? tool → · Submit your own Mistral Medium 3.5 128B benchmark →

Get the weekly "best value AI rig in AUD" email

Price drops on cards and boxes that run local models, plus new models and what you need to run them. One email a week.