Only with CPU offload

Fara 7B at Q4_K_M needs 5.7 GB but only 5.3 GB is addressable, so about 9% of the layers would stream from system RAM at roughly 60 GB/s. Expect around 31 tokens per second — usable for batch work, painful for chat.

91% on GPU 8K context Q4_K_M · 4.7 GB MIT Released 24 Nov 2025 Vision Not in the Ollama library

A web computer-use agent on a Qwen2.5-VL base — it clicks, fills forms and stops for permission. Not a chat model; size it like an 8B with vision.

Hardware requirements What hardware do I need to run Fara 7B? →

At Q4_K_M with an 8K context: a 8 GB GPU (RTX 4060 Laptop) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 4.7 GB
Weights 4.7 GB KV cache @ 8K 0.44 GB Runtime overhead 0.6 GB Over budget 0.4 GB past 5.3 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 15.4 GB 16.5 GB — ~3.0 Reference 11.2 GB over
Q8_0 8.2 GB 9.2 GB — ~7.7 −0.1% ppl 3.9 GB over
Q6_K 6.3 GB 7.4 GB — ~13 −0.4% ppl 2.1 GB over
Q5_K_M 5.5 GB 6.5 GB — ~18 −0.8% ppl 1.2 GB over
Q4_K_M 4.7 GB 5.7 GB — ~31 −1.9% ppl 0.4 GB over
Q3_K_M 3.8 GB 4.8 GB 16K 54 −5.4% ppl Fits
Q2_K 3.2 GB 4.3 GB 26K 63 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ llama-server \
    -hf microsoft/Fara-7B:Q4_K_M \
    -c 8192 -ngl 25

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 4.7 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model

Related models on a GeForce GTX 1660 Super

ModelTotalTok/s est.
Qwen3 8B
8.19B · similar size
Q4_K_M · 6.3 GB ~22 CPU offload
LFM2.5 8B-A1B
8.47B MoE · similar size
Q4_K_M · 5.5 GB ~81 CPU offload
Llama 3.1 8B Instruct
8.03B · similar size
Q4_K_M · 6.1 GB ~25 CPU offload
Gemma 4 E4B
8.0B · similar size
Q4_K_M · 5.2 GB 45 Tight fit
Ling 3.0 Tiny 7.9B-A1.3B
7.9B MoE · similar size
Q4_K_M · 5.1 GB 107 Tight fit
Granite 4.1 8B
8.79B · similar size
Q4_K_M · 6.8 GB ~17 CPU offload
Ministral 3 8B
8.92B · similar size
Q4_K_M · 6.7 GB ~18 CPU offload

Every model against the GeForce GTX 1660 Super →

Fara 7B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
5.7 GB 33 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
5.7 GB 47 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
5.7 GB 14 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
5.7 GB 131 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
5.7 GB 125 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
5.7 GB 48 Runs great

All 114 devices, by tier →