FitMyLLM
TII/Dense

TIIFalcon Mamba 7B

Falcon Mamba 7B from TII: state-space model, 7.27B parameters, 8K context.

chat
7.27B
Parameters
8K
Context length
6
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2024-08-12
Layers
64
KV Heads
1
Head Dim
64
Family
falcon

Quantization Options

Context length:
QuantBitsVRAM @ 8KQuality
Q4_K_M4.89
5.0 GB
4.9 + 0.1 KV
good
Q5_K_S5.57
5.6 GB
5.5 + 0.1 KV
good
Q5_K_M5.7
5.7 GB
5.7 + 0.1 KV
good
Q6_K6.56
6.5 GB
6.4 + 0.1 KV
excellent
Q8_08.5
8.3 GB
8.2 + 0.1 KV
lossless
FP1616
15.1 GB
15.0 + 0.1 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
Ready to run this?Rent by the hour

Rent a GPU and run Falcon Mamba 7B now

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (6)

Run this model

Easiest way to get started·Beginners
Docs ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run falcon:7b

Ollama's default build of this model. For Q4_K_M specifically, pick a tag from ollama.com/library/falcon/tags.

Setup guide
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla K20c
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA Tesla K20m
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA Tesla K20s
5 GB VRAM • 208 GB/s
NVIDIA
NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA

Find the best GPU for Falcon Mamba 7B

Build Hardware for Falcon Mamba 7B
Spec sheet

Falcon Mamba 7B — 7.27B Dense.

Specifications
Parameters
7.27B
Architecture
Dense Transformer
Context Length
8K tokens
Capabilities
chat
Release Date
2024-08-12
Provider
TII
Family
falcon
VRAM requirements
QuantBPWVRAMQuality
Q4_K_M4.894.9 GB94%
Q5_K_S5.575.5 GB96%
Q5_K_M5.75.7 GB96%
Q6_K6.566.4 GB97%
Q8_08.58.2 GB100%
FP161615.0 GB100%
Benchmark scores
MMLU-PRO34.3
MATH40.9
IFEval76.1
BBH37.9
GPQA8.1
MUSR21.2
Run command

Run Falcon Mamba 7B locally with Ollama — needs 4.9 GB VRAM at Q4_K_M:

$ollama run falcon:7b
Compatible GPUs
30 @ Q4_K_M